#920 by GitHub stars

china-qijizhifeng/agentic-harness-engineering

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.

Codex Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`agents/evolve_agent/skills/agent-debugger-cli/SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Not checked yet → After Network or broad shell

8b2a55d97590 → 182ea06e578d

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Not checked yet

First observation → 8b2a55d97590

No earlier version was observed for comparison.

Compare on GitHub

`agents/evolve_agent/skills/nexau-evolution-guide/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

8b2a55d97590 → 182ea06e578d

A local comparison is unavailable. You can inspect the recorded versions on GitHub.

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Not checked yet

First observation → 8b2a55d97590

No earlier version was observed for comparison.

Compare on GitHub

`skills/agentic-harness-engineering/SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

8b2a55d97590 → 182ea06e578d

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Not checked yet

First observation → 8b2a55d97590

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 182ea06e578df7b1d503eca537503c1e4c5a8a58

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/china-qijizhifeng/agentic-harness-engineering.git .hotskills/china-qijizhifeng-agentic-harness-engineering && git -C .hotskills/china-qijizhifeng-agentic-harness-engineering checkout --detach 182ea06e578df7b1d503eca537503c1e4c5a8a58
# Copy each selected skill directory from .hotskills/china-qijizhifeng-agentic-harness-engineering into .agents/skills/<skill-name>/

961GitHub stars

7stars in 7 days

3skills in this repository

2commits in 30 days

Heat

5.3

Star growth, last 7 daysAhead of 78% of tracked repositories
Star growth, last 24 hoursAhead of 71% of tracked repositories
Rank movement, last 7 daysAhead of 16% of tracked repositories
Commits, last 30 daysAhead of 60% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

agent-debugger-cli agents/evolve_agent/skills/agent-debugger-cli
nexau-evolution-guide agents/evolve_agent/skills/nexau-evolution-guide
agentic-harness-engineering skills/agentic-harness-engineering

How it works

Choose a skill

agent-debugger-cli

When your agent uses it

Install and use the bundled agent debugger CLI source to configure adb LLM settings, download Langfuse traces, ask QA questions about traces, and run adb check quality analysis. Use when the task is about agent-debugger CLI workflows, trace debugging, or explaining how adb is configured.

What it loads into context

Frontmatter

112 tokens

Always available to the agent

SKILL.md

2,393 tokens

When the skill is activated

Reference documents

998 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files in this skill
Install
LLM configuration
Trace workflow
Runtime notes
Minimal end-to-end example

Scripts executed separately

_source/agent_debugger_core/__init__.py
_source/agent_debugger_core/cli/__init__.py
_source/agent_debugger_core/cli/adb.py
_source/agent_debugger_core/cli/config_store.py
_source/agent_debugger_core/cli/llm_resolver.py
_source/agent_debugger_core/download.py
_source/agent_debugger_core/runtime/__init__.py
_source/agent_debugger_core/runtime/bootstrap.py
_source/agent_debugger_core/runtime/runner.py
_source/agent_debugger_core/trace_io.py
_source/scripts/build_and_deploy.sh
_source/tests/test_bootstrap.py
_source/tests/test_cli_ask.py
_source/tests/test_cli_ask_records.py
_source/tests/test_cli_check.py
_source/tests/test_cli_help.py
_source/tests/test_config.py
_source/tests/test_download.py
_source/tests/test_golden_diff.sh
_source/tests/test_llm_resolver.py
_source/tests/test_runner_ask.py
_source/tests/test_runner_check_and_retry.py
_source/tests/test_runner_llm_retry.py
_source/tests/test_runtime_configs.py
_source/tests/test_trace_io_inmemory.py
_source/tests/test_trace_io_langfuse.py
_source/tests/test_trace_io_openai.py

Files

SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
SKILL.mdcore8,947 bytes
_source/.gitignoreasset53 bytes
_source/README.mddoc51 bytes
_source/agent_debugger_core/__init__.pyruns22 bytes
_source/agent_debugger_core/cli/__init__.pyruns0 bytes
_source/agent_debugger_core/cli/adb.pyruns10,459 bytes
_source/agent_debugger_core/cli/config_store.pyruns1,961 bytes
_source/agent_debugger_core/cli/llm_resolver.pyruns1,109 bytes
_source/agent_debugger_core/download.pyruns2,510 bytes
_source/agent_debugger_core/runtime/__init__.pyruns0 bytes
_source/agent_debugger_core/runtime/agent_config.yamlasset2,180 bytes
_source/agent_debugger_core/runtime/bootstrap.pyruns1,941 bytes
_source/agent_debugger_core/runtime/runner.pyruns8,106 bytes
_source/agent_debugger_core/runtime/system_prompt.mddoc4,004 bytes
_source/agent_debugger_core/runtime/tool_descriptions/Glob.tool.yamlasset1,110 bytes
_source/agent_debugger_core/runtime/tool_descriptions/WebFetch.tool.yamlasset1,469 bytes
_source/agent_debugger_core/runtime/tool_descriptions/WebSearch.tool.yamlasset1,166 bytes
_source/agent_debugger_core/runtime/tool_descriptions/complete_task.tool.yamlasset985 bytes
_source/agent_debugger_core/runtime/tool_descriptions/list_directory.tool.yamlasset1,133 bytes
_source/agent_debugger_core/runtime/tool_descriptions/read_file.tool.yamlasset1,057 bytes
_source/agent_debugger_core/runtime/tool_descriptions/replace.tool.yamlasset4,091 bytes
_source/agent_debugger_core/runtime/tool_descriptions/run_shell_command.tool.yamlasset2,019 bytes
_source/agent_debugger_core/runtime/tool_descriptions/search_file_content.tool.yamlasset1,264 bytes
_source/agent_debugger_core/runtime/tool_descriptions/write_file.tool.yamlasset778 bytes
_source/agent_debugger_core/trace_io.pyruns5,301 bytes
_source/pyproject.tomlasset844 bytes
_source/scripts/build_and_deploy.shruns382 bytes
_source/tests/fixtures/in_memory_tracer_sample.jsonasset605 bytes
_source/tests/fixtures/langfuse_sample.jsonasset554 bytes
_source/tests/fixtures/openai_messages_sample.jsonasset192 bytes
_source/tests/test_bootstrap.pyruns1,316 bytes
_source/tests/test_cli_ask.pyruns1,862 bytes
_source/tests/test_cli_ask_records.pyruns1,562 bytes
_source/tests/test_cli_check.pyruns1,885 bytes
_source/tests/test_cli_help.pyruns1,788 bytes
_source/tests/test_config.pyruns1,691 bytes
_source/tests/test_download.pyruns1,269 bytes
_source/tests/test_golden_diff.shruns2,657 bytes
_source/tests/test_llm_resolver.pyruns1,540 bytes
_source/tests/test_runner_ask.pyruns1,841 bytes
_source/tests/test_runner_check_and_retry.pyruns3,055 bytes
_source/tests/test_runner_llm_retry.pyruns1,991 bytes
_source/tests/test_runtime_configs.pyruns1,295 bytes
_source/tests/test_trace_io_inmemory.pyruns664 bytes
_source/tests/test_trace_io_langfuse.pyruns612 bytes
_source/tests/test_trace_io_openai.pyruns1,044 bytes

Read SKILL.md


# Agent Debugger CLI

Use this skill when you need the standalone `adb` CLI that ships inside the bundled `_source/` package in this directory.

## Files in this skill

- `_source/`: bundled open-source package that exposes the `adb` command.

## Install

The package is declared as a path source in the project root `pyproject.toml`, so a top-level `uv sync` already installs it. To install standalone from this skill directory:

```bash
python -m pip install ./_source

View the complete source on GitHub

nexau-evolution-guide

When your agent uses it

NexAU agent evolution reference for a simple starting agent. Use when adding tools, middleware, sub-agents, or skills during evolution. Covers all available components, YAML config schema, and creation guides. Reference docs in reference/ for deep dives.

What it loads into context

Frontmatter

59 tokens

Always available to the agent

SKILL.md

3,546 tokens

When the skill is activated

Reference documents

17,972 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Current Agent Baseline
Validation
Adding Tools
Adding Middleware
Adding Sub-Agents
Adding Skills
YAML Config Reference (`code_agent.yaml`)
Reference Docs

Scripts executed separately

scripts/validate_agent.py

Files

SKILL.mdcore14,273 bytes
SKILL.mdcore14,273 bytes
SKILL.mdcore14,273 bytes
SKILL.mdcore14,273 bytes
SKILL.mdcore14,273 bytes
SKILL.mdcore14,273 bytes
SKILL.mdcore14,273 bytes
SKILL.mdcore14,273 bytes
reference/agents.mddoc3,484 bytes
reference/hooks.mddoc14,091 bytes
reference/llms.mddoc1,262 bytes
reference/sandbox.mddoc36,065 bytes
reference/skills.mddoc15,132 bytes
reference/tools.mddoc8,474 bytes
scripts/validate_agent.pyruns16,788 bytes

Read SKILL.md


# NexAU Evolution Guide — Simple Agent Starting Point

The code agent starts **simple**: a single `run_shell_command` tool, no middleware, no skills, no sub-agents. Evolution progressively adds components to improve performance. This guide covers **what you can add** and **how to add it**.

## Current Agent Baseline

```yaml
# workspace/code_agent.yaml (starting state)
type: agent
tools:
  - name: run_shell_command
    yaml_path: ./tool_descriptions/run_shell_command.tool.yaml
    binding: tools.shell_tools:run_shell_command
# No middleware, no skills, no sub_agents

View the complete source on GitHub

agentic-harness-engineering

When your agent uses it

Agent Harness Evolution — 基于 HARNESS.md v1.0 规范的评估、审计与改进工作流。加载后自动检查当前 workspace 结构合规性，引导 evidence-driven 的 Harness 改进。当用户要求做 Harness 审计、初始化 Agent workspace、生成或验证 Change Manifest、对 harness 组件做 evidence-driven 改进，或反复出现同一类失败模式时触发。

What it loads into context

Frontmatter

101 tokens

Always available to the agent

SKILL.md

1,945 tokens

When the skill is activated

Reference documents

9,439 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

什么时候加载这个 Skill
工作流 1：Harness Audit
工作流 2：Generate Change Manifest
工作流 3：Verify Changes
工作流 4：Harness 初始化
原则
参考

Scripts executed separately

references/examples/minimal-workspace/tools/example_tool.py
scripts/ci.sh
scripts/generate_manifest.py
scripts/init_harness.py
scripts/validate_harness.py
scripts/verify_manifest.py

Files

SKILL.mdcore7,286 bytes
profiles/codex.yamlasset869 bytes
profiles/hermes.yamlasset885 bytes
profiles/openclaw.yamlasset918 bytes
references/HARNESS.mddoc14,299 bytes
references/PROJECT_README.mddoc7,127 bytes
references/analysis/README.mddoc702 bytes
references/analysis/detail-template.mddoc414 bytes
references/analysis/overview-template.mddoc843 bytes
references/change-manifest-schema.jsonasset5,335 bytes
references/directory-template.mddoc2,015 bytes
references/docs/results-format.mddoc2,403 bytes
references/docs/rollback-strategy.mddoc4,556 bytes
references/examples/minimal-workspace/AGENTS.mddoc161 bytes
references/examples/minimal-workspace/MEMORY.mddoc60 bytes
references/examples/minimal-workspace/SOUL.mddoc66 bytes
references/examples/minimal-workspace/manifests/example_manifest.jsonasset755 bytes
references/examples/minimal-workspace/tool_descriptions/example.tool.yamlasset230 bytes
references/examples/minimal-workspace/tools/example_tool.pyruns69 bytes
references/examples/trace-sample/analysis-overview.mddoc1,477 bytes
references/examples/trace-sample/task-t042-search-truncation.mddoc2,060 bytes
scripts/ci.shruns4,342 bytes
scripts/generate_manifest.pyruns7,790 bytes
scripts/init_harness.pyruns4,731 bytes
scripts/validate_harness.pyruns12,383 bytes
scripts/verify_manifest.pyruns5,988 bytes

Read SKILL.md


# AHE Skill — Agent Harness Evolution

> 将 [AHE（Agentic Harness Engineering）](https://arxiv.org/abs/2604.25850) 论文的核心模式实现为可执行的 Skill。
> 遵循 [HARNESS.md v1.0](references/HARNESS.md) 规范。

---

## 什么时候加载这个 Skill

- **做 Harness Audit** — 想知道当前 workspace 的结构是否符合规范 → 加载 skill，运行 audit 流程
- **改了一个核心组件** — 修改了 system prompt、工具、middleware 等 → 加载 skill，生成 Change Manifest
- **想验证上次修改** — 之前生成了 Change Manifest 但还没验证 → 加载 skill，运行 verify 流程
- **Harness 反复出同一个问题** — 同一个失败模式出现 2+ 次 → 加载 skill，做 evidence-driven 改进
- **搭建新 Agent** — 初始化一个新的 Agent workspace → 加载 skill，用 HARNESS.md 模板初始化

View the complete source on GitHub

Skills included

agent-debugger-cli
nexau-evolution-guide
agentic-harness-engineering

Repository facts

License: MIT
Created: Apr 23, 2026
Last pushed: Oct 30, 2026
Forks: 104
Open issues: 5
Project activity: Active

Rank over the last 12 weeks

Now #920 · best #626 · down 181 in 30 days

#908 on Nov 1
#911 on Nov 2
#919 on Nov 3
#920 on Nov 4
#921 on Nov 5
#920 since Nov 6

62 earlier periods

#635 on Aug 2
#663 on Aug 6
#621 on Aug 8
#625 on Aug 9
#652 on Aug 10
#657 on Aug 11
#653 on Aug 12
#648 on Aug 13
#646 on Aug 14
#626 on Aug 15
#638 on Aug 16
#664 on Aug 18
#648 on Aug 19
#649 on Aug 20
#653 on Aug 21
#654 on Aug 23
#669 on Aug 24
#672 on Aug 27
#693 on Aug 28
#639 on Aug 29
#637 on Aug 30
#668 on Aug 31
#670 on Sep 2
#647 on Sep 5
#683 on Sep 7
#702 on Sep 8
#693 on Sep 9
#695 on Sep 10
#677 on Sep 11
#678 on Sep 12
#701 on Sep 14
#706 on Sep 16
#709 on Sep 17
#670 on Sep 19
#688 on Sep 20
#704 on Sep 21
#723 on Sep 22
#689 on Sep 24
#672 on Sep 26
#750 on Sep 29
#726 on Sep 30
#698 on Oct 2
#681 on Oct 3
#717 on Oct 5
#729 on Oct 6
#739 on Oct 7
#780 on Oct 8
#730 on Oct 11
#748 on Oct 12
#765 on Oct 16
#745 on Oct 17
#726 on Oct 18
#770 on Oct 19
#775 on Oct 20
#784 on Oct 21
#774 on Oct 23
#738 on Oct 24
#889 on Oct 25
#899 on Oct 28
#903 on Oct 29
#904 on Oct 30
#907 on Oct 31

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 26 notes

agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/agent-debugger-cli/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
agents/evolve_agent/skills/nexau-evolution-guide/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
5 dangerous shell commandsin 3 files: nexau-evolution-guide/reference/tools.md:101 agentic-harness-engineering/scripts/ci.sh:64 agent-debugger-cli/_source/scripts/build_and_deploy.sh:5
74 network referencesin 24 files: nexau-evolution-guide/reference/hooks.md:191 nexau-evolution-guide/reference/llms.md:15 agent-debugger-cli/_source/tests/test_download.py:22 and 21 more
No hidden or obfuscated text
No instruction overrides
34 executable scriptsin 34 files: agent-debugger-cli/_source/agent_debugger_core/__init__.py:1 agent-debugger-cli/_source/agent_debugger_core/cli/__init__.py:1 agent-debugger-cli/_source/agent_debugger_core/cli/adb.py:1 and 31 more
53 references to secretsin 22 files: agent-debugger-cli/_source/tests/test_config.py:17 agent-debugger-cli/_source/tests/test_llm_resolver.py:17 agent-debugger-cli/SKILL.md:38 and 19 more
No requests to vote in Hot

Show all 166 signals by file

`agents/evolve_agent/skills/agent-debugger-cli/SKILL.md`

Network accessline 38
```
[Credential-related source omitted]
```
Access to secretsline 38
```
[Credential-related source omitted]
```
Network accessline 44
```
[Credential-related source omitted]
```
Access to secretsline 44
```
[Credential-related source omitted]
```
Access to secretsline 52
```
[Credential-related source omitted]
```
Access to secretsline 53
```
[Credential-related source omitted]
```
Network accessline 282
```
[Credential-related source omitted]
```
Network accessline 283
```
[Credential-related source omitted]
```
Access to secretsline 283
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/init.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/init.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/adb.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/config_store.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 18
```
[Credential-related source omitted]
```
Access to secretsline 43
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/llm_resolver.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 19
```
[Credential-related source omitted]
```
Access to secretsline 20
```
[Credential-related source omitted]
```
Access to secretsline 27
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/download.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/init.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/agent_config.yaml`

Access to secretsline 12
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/bootstrap.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 23
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/runner.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 68
```
[Credential-related source omitted]
```
Access to secretsline 74
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/Glob.tool.yaml`

Network accessline 30

- pattern   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 32

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/WebFetch.tool.yaml`

Network accessline 34

- url   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 36

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/WebSearch.tool.yaml`

Access to secretsline 13
```
[Credential-related source omitted]
```

Network accessline 29

- query   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 31

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/complete_task.tool.yaml`

Network accessline 26

- result   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 28

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/list_directory.tool.yaml`

Network accessline 34

- dir_path   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 36

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/read_file.tool.yaml`

Network accessline 26

- file_path   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 28

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/replace.tool.yaml`

Network accessline 94

- new_string   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 96

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/run_shell_command.tool.yaml`

Network accessline 50

- command   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 52

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/search_file_content.tool.yaml`

Network accessline 31

- pattern   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 33

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/write_file.tool.yaml`

Network accessline 25

- content   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 27

$schema: http://json-schema.org/draft-07/schema#

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/trace_io.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/pyproject.toml`

Network accessline 11

license = { text = "MIT" } dependencies = [     "nexau @ git+https://github.com/hzhua/nexau.git@28511d9f0362191a6c378fd441b2be55309a9e32",

Network accessline 12

dependencies = [     "nexau @ git+https://github.com/hzhua/nexau.git@28511d9f0362191a6c378fd441b2be55309a9e32",     "langfuse>=2.0.0",

Network accessline 13

"nexau @ git+https://github.com/hzhua/nexau.git@28511d9f0362191a6c378fd441b2be55309a9e32",

`agents/evolve_agent/skills/agent-debugger-cli/_source/scripts/build_and_deploy.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

Dangerous shell operationline 5

rm -rf "$OUT_DIR" "$HERE/build" "$HERE"/*.egg-info

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_bootstrap.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_ask.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 13
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_ask_records.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 15
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_check.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 19
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_help.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_config.py`

Executable scriptline 1
```
Executable file
```
Network accessline 15
```
[Credential-related source omitted]
```
Network accessline 16
```
[Credential-related source omitted]
```
Network accessline 17
```
[Credential-related source omitted]
```
Access to secretsline 17
```
[Credential-related source omitted]
```
Access to secretsline 18
```
[Credential-related source omitted]
```
Access to secretsline 22
```
[Credential-related source omitted]
```
Access to secretsline 29
```
[Credential-related source omitted]
```
Access to secretsline 30
```
[Credential-related source omitted]
```
Access to secretsline 34
```
[Credential-related source omitted]
```
Access to secretsline 39
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_download.py`

Executable scriptline 1
```
Executable file
```

Network accessline 22

with patch("agent_debugger_core.download._make_client", return_value=fake_client):         out_path = download_langfuse_trace(             url="https://lf.example/project/proj_01/traces/trace_abc",

Network accessline 23

out_path = download_langfuse_trace(             url="https://lf.example/project/proj_01/traces/trace_abc",             ak="pk", sk="sk",

Network accessline 24

url="https://lf.example/project/proj_01/traces/trace_abc",

Network accessline 33

monkeypatch.setenv("HOME", str(tmp_path))     with pytest.raises(DownloadError):         download_langfuse_trace(url="https://nope", ak="", sk="")

Network accessline 35

download_langfuse_trace(url="https://nope", ak="", sk="")

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_golden_diff.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Access to secretsline 3
```
[Credential-related source omitted]
```
Access to secretsline 33
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_llm_resolver.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 17
```
[Credential-related source omitted]
```
Access to secretsline 23
```
[Credential-related source omitted]
```
Access to secretsline 28
```
[Credential-related source omitted]
```
Access to secretsline 30
```
[Credential-related source omitted]
```
Access to secretsline 35
```
[Credential-related source omitted]
```
Access to secretsline 40
```
[Credential-related source omitted]
```
Access to secretsline 41
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_ask.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 31
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_check_and_retry.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 12
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_llm_retry.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 11
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runtime_configs.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_inmemory.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_langfuse.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_openai.py`

Executable scriptline 1
```
Executable file
```

`agents/evolve_agent/skills/nexau-evolution-guide/SKILL.md`

Network accessline 92

- param_name   additionalProperties: false   $schema: http://json-schema.org/draft-07/schema#

Network accessline 94

$schema: http://json-schema.org/draft-07/schema#

Access to secretsline 247
```
[Credential-related source omitted]
```
Access to secretsline 271
```
[Credential-related source omitted]
```
Access to secretsline 272
```
[Credential-related source omitted]
```
Access to secretsline 308
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/nexau-evolution-guide/reference/agents.md`

Access to secretsline 27
```
[Credential-related source omitted]
```
Access to secretsline 94
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/nexau-evolution-guide/reference/hooks.md`

Network accessline 191

- name: "backup-gateway"           llm_config:             base_url: "https://backup.example.com/v1"

Network accessline 192
```
[Credential-related source omitted]
```

Network accessline 193

base_url: "https://backup.example.com/v1"

Access to secretsline 194
```
[Credential-related source omitted]
```

Network accessline 196

llm_config:             model: "gpt-4o"             base_url: "https://emergency.example.com/v1"

Network accessline 197
```
[Credential-related source omitted]
```

Network accessline 198

base_url: "https://emergency.example.com/v1"

Access to secretsline 199
```
[Credential-related source omitted]
```
Network accessline 212
```
[Credential-related source omitted]
```
Network accessline 213
```
[Credential-related source omitted]
```
Network accessline 214
```
[Credential-related source omitted]
```
Access to secretsline 214
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/nexau-evolution-guide/reference/llms.md`

Network accessline 15

llm_config = LLMConfig(     model="gpt-4",     base_url="[https://api.openai.com/v1](https://api.openai.com/v1)",

Network accessline 16
```
[Credential-related source omitted]
```

Network accessline 17

base_url="[https://api.openai.com/v1](https://api.openai.com/v1)",

Access to secretsline 18
```
[Credential-related source omitted]
```

Network accessline 24

llm_config = LLMConfig(     model="claude-3-sonnet-20240229",     base_url="[https://api.anthropic.com](https://api.anthropic.com)", # or your proxy URL

Network accessline 25
```
[Credential-related source omitted]
```

Network accessline 26

base_url="[https://api.anthropic.com](https://api.anthropic.com)", # or your proxy URL

Access to secretsline 27
```
[Credential-related source omitted]
```

Network accessline 33

llm_config = LLMConfig(     model="custom-model",     base_url="http://localhost:8000/v1",

Network accessline 34
```
[Credential-related source omitted]
```
Network accessline 35
```
base_url="http://localhost:8000/v1",
```
Access to secretsline 36
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/nexau-evolution-guide/reference/sandbox.md`

Network accessline 15

- **LocalSandbox**: Executes commands directly on the local system (development/testing only) - **E2BSandbox**: Cloud-based sandboxes using [E2B](https://e2b.dev) (production-ready)

Network accessline 16

- **E2BSandbox**: Cloud-based sandboxes using [E2B](https://e2b.dev) (production-ready)

Access to secretsline 120
```
[Credential-related source omitted]
```
Access to secretsline 133
```
[Credential-related source omitted]
```
Access to secretsline 495
```
[Credential-related source omitted]
```

`agents/evolve_agent/skills/nexau-evolution-guide/reference/skills.md`

Network accessline 435

Check [Claude Skill](https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices) for how to write a good skill.

`agents/evolve_agent/skills/nexau-evolution-guide/reference/tools.md`

Access to secretsline 78
```
[Credential-related source omitted]
```

Dangerous shell operationline 101

# Note: Using eval() is unsafe for untrusted input. This is for demonstration.

Dangerous shell operationline 102

result = eval(expression, {"__builtins__": None}, {})

Network accessline 127

- expression   additionalProperties: false   $schema: [http://json-schema.org/draft-07/schema#](http://json-schema.org/draft-07/schema#)

Network accessline 129

$schema: [http://json-schema.org/draft-07/schema#](http://json-schema.org/draft-07/schema#)

`agents/evolve_agent/skills/nexau-evolution-guide/scripts/validate_agent.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/agentic-harness-engineering/SKILL.md`

Network accessline 8

> 将 [AHE（Agentic Harness Engineering）](https://arxiv.org/abs/2604.25850) 论文的核心模式实现为可执行的 Skill。

Network accessline 205

- [HARNESS.md v1.0 — 完整规范文档](references/HARNESS.md) - [Change Manifest JSON Schema](references/change-manifest-schema.json) - [AHE 论文](https://arxiv.org/abs/2604.25850)

Network accessline 206

- [Change Manifest JSON Schema](references/change-manifest-schema.json) - [AHE 论文](https://arxiv.org/abs/2604.25850) - [AHE 代码仓库](https://github.com/china-qijizhifeng/agentic-harness-engineering)

Network accessline 207

- [AHE 论文](https://arxiv.org/abs/2604.25850)

Network accessline 208

- [AHE 代码仓库](https://github.com/china-qijizhifeng/agentic-harness-engineering)

`skills/agentic-harness-engineering/references/HARNESS.md`

Network accessline 4

> 让任何 Agent（Hermes / OpenClaw / Claude Code / Codex / Cursor）的"外挂系统"有统一的语言、结构和可演化能力。 > > 灵感来源：[Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://arxiv.org/abs/2604.25850)（复旦 & 北大, 2026）

Network accessline 6

> 灵感来源：[Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://arxiv.org/abs/2604.25850)（复旦 & 北大, 2026）

Network accessline 334

- [agentic-harness-engineering skill](../SKILL.md) — 实现本规范的 Skill（含 audit、generate-manifest、verify 功能） - [AHE 论文](https://arxiv.org/abs/2604.25850) — 本规范的学术基础（复旦 & 北大，2026）

Network accessline 335

- [AHE 论文](https://arxiv.org/abs/2604.25850) — 本规范的学术基础（复旦 & 北大，2026）

`skills/agentic-harness-engineering/references/PROJECT_README.md`

Network accessline 22

复旦 & 北大的 [AHE 论文](https://arxiv.org/abs/2604.25850) 证明：用三层可观测性驱动 Harness 自动演化，可以把 coding agent 的 Terminal-Bench 2 成绩从 69.7% 推到 77.0%，超越了人类手写的 Codex CLI。

Network accessline 157

- **[Agentic Harness Engineering](https://arxiv.org/abs/2604.25850)** — Jiahang Lin, Shichun Liu, Chengjun Pan 等（复旦 & 北大, 2026）

Network accessline 162

- **[Agent Harness for LLM Agents: A Survey](https://huggingface.co/datasets/GloriaaaM/LLM-Agent-Harness-Survey)** — Harness 六组件形式化定义 H=(E,T,C,S,L,V)

`skills/agentic-harness-engineering/references/change-manifest-schema.json`

Network accessline 1

{   "$schema": "http://json-schema.org/draft-07/schema#",

Network accessline 2

"$schema": "http://json-schema.org/draft-07/schema#",

`skills/agentic-harness-engineering/references/examples/minimal-workspace/tools/example_tool.py`

Executable scriptline 1
```
Executable file
```

`skills/agentic-harness-engineering/scripts/ci.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Dangerous shell operationline 64
```
rm -rf "$TMPDIR"
```
Dangerous shell operationline 85
```
rm -rf "$TMPDIR2"
```

`skills/agentic-harness-engineering/scripts/generate_manifest.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/agentic-harness-engineering/scripts/init_harness.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/agentic-harness-engineering/scripts/validate_harness.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/agentic-harness-engineering/scripts/verify_manifest.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 139 facts

Network access in code of the SKILL.mdagent-debugger-cli/SKILL.md:38High confidence
Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueagent-debugger-cli/SKILL.md:38Low confidence
Network access in code of the SKILL.mdagent-debugger-cli/SKILL.md:44High confidence
Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueagent-debugger-cli/SKILL.md:44Low confidence
Access to secrets in prose of the SKILL.mdagent-debugger-cli/SKILL.md:52Low confidence
Access to secrets in prose of the SKILL.mdagent-debugger-cli/SKILL.md:53Low confidence
Network access in code of the SKILL.mdagent-debugger-cli/SKILL.md:282High confidence
Network access in code of the SKILL.mdagent-debugger-cli/SKILL.md:283High confidence
Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueagent-debugger-cli/SKILL.md:283Low confidence
Executable script in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/__init__.py:1High confidence
Executable script in prose of a file that runsagent-debugger-cli/_source/agent_debugger_core/cli/__init__.py:1Low confidence
Executable script in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/cli/adb.py:1High confidence
Executable script in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/cli/config_store.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/agent_debugger_core/cli/config_store.py:18Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/agent_debugger_core/cli/config_store.py:43Low confidence
Executable script in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/cli/llm_resolver.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/agent_debugger_core/cli/llm_resolver.py:19Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/agent_debugger_core/cli/llm_resolver.py:20Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/agent_debugger_core/cli/llm_resolver.py:27Low confidence
Executable script in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/download.py:1High confidence
Executable script in prose of a file that runsagent-debugger-cli/_source/agent_debugger_core/runtime/__init__.py:1Low confidence
Executable script in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/runtime/bootstrap.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/agent_debugger_core/runtime/bootstrap.py:23Low confidence
Executable script in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/runtime/runner.py:1High confidence
Access to secrets in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/runtime/runner.py:68High confidence
Access to secrets in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/runtime/runner.py:74High confidence
Executable script in code of a file that runsagent-debugger-cli/_source/agent_debugger_core/trace_io.py:1High confidence
Executable script in code of a file that runsagent-debugger-cli/_source/scripts/build_and_deploy.sh:1High confidence
Dangerous shell operation in code of a file that runsagent-debugger-cli/_source/scripts/build_and_deploy.sh:5High confidence
Executable script in code of a testagent-debugger-cli/_source/tests/test_bootstrap.py:1Low confidence
Executable script in code of a testagent-debugger-cli/_source/tests/test_cli_ask.py:1Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/tests/test_cli_ask.py:13Low confidence
Executable script in code of a testagent-debugger-cli/_source/tests/test_cli_ask_records.py:1Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/tests/test_cli_ask_records.py:15Low confidence
Executable script in code of a testagent-debugger-cli/_source/tests/test_cli_check.py:1Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/tests/test_cli_check.py:19Low confidence
Executable script in code of a testagent-debugger-cli/_source/tests/test_cli_help.py:1Low confidence
Executable script in code of a testagent-debugger-cli/_source/tests/test_config.py:1Low confidence
Network access in code of a testagent-debugger-cli/_source/tests/test_config.py:15Low confidence
Network access in code of a testagent-debugger-cli/_source/tests/test_config.py:16Low confidence
Network access in code of a testagent-debugger-cli/_source/tests/test_config.py:17Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/tests/test_config.py:17Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/tests/test_config.py:18Low confidence
Access to secrets in code of a testagent-debugger-cli/_source/tests/test_config.py:22Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/tests/test_config.py:29Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/tests/test_config.py:30Low confidence
Access to secrets in code of a testagent-debugger-cli/_source/tests/test_config.py:34Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valueagent-debugger-cli/_source/tests/test_config.py:39Low confidence
Executable script in code of a testagent-debugger-cli/_source/tests/test_download.py:1Low confidence
Network access in code of a testagent-debugger-cli/_source/tests/test_download.py:22Low confidence

and 89 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md agents/evolve_agent/skills/agent-debugger-cli/SKILL.md	`.claude/skills/<skill-name>/`
Codex	Native	Manifest skills/agentic-harness-engineering/references/examples/minimal-workspace/AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md agents/evolve_agent/skills/agent-debugger-cli/SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md agents/evolve_agent/skills/agent-debugger-cli/SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md agents/evolve_agent/skills/agent-debugger-cli/SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md agents/evolve_agent/skills/agent-debugger-cli/SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![china-qijizhifeng/agentic-harness-engineering on hotskills](https://hotskills.dev/badge/china-qijizhifeng-agentic-harness-engineering.svg)](https://hotskills.dev/skill/china-qijizhifeng-agentic-harness-engineering/)

china-qijizhifeng/agentic-harness-engineering

History

agents/evolve_agent/skills/agent-debugger-cli/SKILL.md

agents/evolve_agent/skills/nexau-evolution-guide/SKILL.md

skills/agentic-harness-engineering/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

agent-debugger-cli

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

nexau-evolution-guide

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

agentic-harness-engineering

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

agents/evolve_agent/skills/agent-debugger-cli/SKILL.md

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/__init__.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/__init__.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/adb.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/config_store.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/llm_resolver.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/download.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/__init__.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/agent_config.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/bootstrap.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/runner.py

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/Glob.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/WebFetch.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/WebSearch.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/complete_task.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/list_directory.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/read_file.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/replace.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/run_shell_command.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/search_file_content.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/write_file.tool.yaml

agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/trace_io.py

agents/evolve_agent/skills/agent-debugger-cli/_source/pyproject.toml

agents/evolve_agent/skills/agent-debugger-cli/_source/scripts/build_and_deploy.sh

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_bootstrap.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_ask.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_ask_records.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_check.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_help.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_config.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_download.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_golden_diff.sh

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_llm_resolver.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_ask.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_check_and_retry.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_llm_retry.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runtime_configs.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_inmemory.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_langfuse.py

agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_openai.py

agents/evolve_agent/skills/nexau-evolution-guide/SKILL.md

agents/evolve_agent/skills/nexau-evolution-guide/reference/agents.md

agents/evolve_agent/skills/nexau-evolution-guide/reference/hooks.md

agents/evolve_agent/skills/nexau-evolution-guide/reference/llms.md

agents/evolve_agent/skills/nexau-evolution-guide/reference/sandbox.md

`agents/evolve_agent/skills/agent-debugger-cli/SKILL.md`

`agents/evolve_agent/skills/nexau-evolution-guide/SKILL.md`

`skills/agentic-harness-engineering/SKILL.md`

`agents/evolve_agent/skills/agent-debugger-cli/SKILL.md`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/init.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/init.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/adb.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/config_store.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/cli/llm_resolver.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/download.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/init.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/agent_config.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/bootstrap.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/runner.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/Glob.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/WebFetch.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/WebSearch.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/complete_task.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/list_directory.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/read_file.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/replace.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/run_shell_command.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/search_file_content.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/runtime/tool_descriptions/write_file.tool.yaml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/agent_debugger_core/trace_io.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/pyproject.toml`

`agents/evolve_agent/skills/agent-debugger-cli/_source/scripts/build_and_deploy.sh`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_bootstrap.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_ask.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_ask_records.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_check.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_cli_help.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_config.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_download.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_golden_diff.sh`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_llm_resolver.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_ask.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_check_and_retry.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runner_llm_retry.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_runtime_configs.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_inmemory.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_langfuse.py`

`agents/evolve_agent/skills/agent-debugger-cli/_source/tests/test_trace_io_openai.py`

`agents/evolve_agent/skills/nexau-evolution-guide/SKILL.md`

`agents/evolve_agent/skills/nexau-evolution-guide/reference/agents.md`

`agents/evolve_agent/skills/nexau-evolution-guide/reference/hooks.md`

`agents/evolve_agent/skills/nexau-evolution-guide/reference/llms.md`

`agents/evolve_agent/skills/nexau-evolution-guide/reference/sandbox.md`

`agents/evolve_agent/skills/nexau-evolution-guide/reference/skills.md`

`agents/evolve_agent/skills/nexau-evolution-guide/reference/tools.md`

`agents/evolve_agent/skills/nexau-evolution-guide/scripts/validate_agent.py`

`skills/agentic-harness-engineering/SKILL.md`

`skills/agentic-harness-engineering/references/HARNESS.md`

`skills/agentic-harness-engineering/references/PROJECT_README.md`

`skills/agentic-harness-engineering/references/change-manifest-schema.json`

`skills/agentic-harness-engineering/references/examples/minimal-workspace/tools/example_tool.py`

`skills/agentic-harness-engineering/scripts/ci.sh`

`skills/agentic-harness-engineering/scripts/generate_manifest.py`

`skills/agentic-harness-engineering/scripts/init_harness.py`

`skills/agentic-harness-engineering/scripts/validate_harness.py`

`skills/agentic-harness-engineering/scripts/verify_manifest.py`