Menu

Not in the top 1,000 by GitHub stars

exadel-inc/agentic-readiness-assessment

Audits a repository for how ready it is for AI coding agents, and returns a prioritized fix backlog with evidence for every finding.

Claude CodeEngineering

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

skills/agent-tool-call-latency/SKILL.md

Week of Nov 2, 2026 · +1 / −3 lines

Before Not checked yet → After Network or broad shell

1313702ad53e → ea984d781338

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 → 1313702ad53e

No earlier version was observed for comparison.

Compare on GitHub

skills/agentic-readiness-assessment/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

1313702ad53e → ea984d781338

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 → 1313702ad53e

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit ea984d78133871c5014ddcbdabc8532058f3f6a2

git clone --filter=blob:none --no-checkout https://github.com/exadel-inc/agentic-readiness-assessment.git .hotskills/exadel-inc-agentic-readiness-assessment && git -C .hotskills/exadel-inc-agentic-readiness-assessment checkout --detach ea984d78133871c5014ddcbdabc8532058f3f6a2 # Copy each selected skill directory from .hotskills/exadel-inc-agentic-readiness-assessment into .claude/skills/<skill-name>/
25GitHub stars
0stars in 7 days
2skills in this repository
30commits in 30 days

Heat

1.7
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

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

Stars over time

Oct 25, 2026Oct 31, 202625

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

agent-tool-call-latency

When your agent uses it

Measures every agent tool call on this machine from local session history (the user's chat logs), in any harness, finds where the time goes, and ranks fixes for slow commands, harness overhead and wasted waiting. Use when the user asks why their agents are slow, where agent run time goes, or how to cut the time agents spend waiting on tools.

What it loads into context

Frontmatter

130 tokens

Always available to the agent

SKILL.md

2,492 tokens

When the skill is activated

Reference documents

11,075 tokens

Loaded on request

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

The playbook

  1. Guardrails
  2. Phase 1: Inventory
  3. Phase 2: Measure
  4. Phase 3: Diagnose
  5. Phase 4: Decisions
  6. Phase 5: Execution
  7. Phase 6: Report

Scripts executed separately

  • scripts/adapters/antigravity.py
  • scripts/adapters/claude_code.py
  • scripts/adapters/codex.py
  • scripts/adapters/cursor.py
  • scripts/adapters/hooklog.py
  • scripts/adapters/t3code.py
  • scripts/aggregate.py
  • scripts/common.py
  • scripts/extract.py
  • scripts/hook_capture.py
  • scripts/validate_calls.py
  • tests/test_scripts.py

Files

  • ../../.claude-plugin/marketplace.jsonasset969 bytes
  • ../../.claude-plugin/plugin.jsonasset824 bytes
  • ../../examples/agent-tool-call-latency/report.mddoc19,535 bytes
  • SKILL.mdcore10,532 bytes
  • SKILL.mdcore10,532 bytes
  • agents/openai.yamlasset355 bytes
  • references/ADAPTERS.mddoc7,062 bytes
  • references/BENCHMARK.mddoc2,516 bytes
  • references/CAUSES.mddoc9,175 bytes
  • references/SCHEMA.mddoc3,380 bytes
  • scripts/adapters/antigravity.pyruns4,727 bytes
  • scripts/adapters/claude_code.pyruns4,361 bytes
  • scripts/adapters/codex.pyruns5,950 bytes
  • scripts/adapters/cursor.pyruns3,399 bytes
  • scripts/adapters/hooklog.pyruns2,457 bytes
  • scripts/adapters/t3code.pyruns1,995 bytes
  • scripts/aggregate.pyruns16,560 bytes
  • scripts/common.pyruns9,902 bytes
  • scripts/extract.pyruns6,205 bytes
  • scripts/hook_capture.pyruns3,265 bytes
  • scripts/validate_calls.pyruns4,376 bytes
  • tests/test_scripts.pyruns24,596 bytes
Read SKILL.md

# Agent tool-call latency

An **audit** of how long the agent's tool calls take, across every harness the user runs (CLI agents, desktop apps, frontends that drive other agents), measured from the user's own session history. It runs as **inventory**, **measure**, **diagnose**, **decisions** (the user rules on each fix), **execution** (approved fixes only) and **report**.

The skill's scripts are harness-neutral: adapters turn each harness's history into one [call record](references/SCHEMA.md) format, and everything after extraction reads only that format. A harness without a built-in adapter gets one written during the inventory.

Work in `~/.cache/agent-tool-call-latency/<today>/` (the **work directory**; create it first); `<skill>` below is this file's folder. The default window is 30 days; an argument narrows the window, the harnesses or the projects, and the phases stay the same.

## Guardrails

- **History is read-only.** Session files and databases are the user's chat history: open them read-only and never write, move or delete anything under a harness's directories.
- **Records stay local.** `calls.jsonl` holds commands, with secrets masked. It stays in the work directory; the report names command patterns, not full commands.
- **Causes are confirmed before they are ranked.** An entry in [CAUSES.md](references/CAUSES.md) is a hypothesis until this run confirms it on this machine with a benchmark, the harness's current documentation, a `path:line` in the repository, or the raw log.
- **Fixes remove waste.** Queueing, overhead, repeated start-up, killed and re-run work, foreground waiting, and tests the change cannot affect are waste. A change that makes a check prove less is not a fix.
View the complete source on GitHub

Skills included

  • agent-tool-call-latency
  • agentic-readiness-assessment

Repository facts

License
Apache-2.0
Created
Aug 28, 2026
Last pushed
Nov 3, 2026
Forks
3
Open issues
0
Project activity
Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

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

Show 2 notes
  • skills/agent-tool-call-latency/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/agentic-readiness-assessment/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 59 signals by file

.claude-plugin/marketplace.json

  • Network accessline 1
    {   "$schema": "https://json.schemastore.org/claude-code-marketplace.json",
  • Network accessline 2
    "$schema": "https://json.schemastore.org/claude-code-marketplace.json",
  • Network accessline 5
    "owner": {     "name": "Exadel",     "url": "https://exadel.com"
  • Network accessline 6
    "name": "Exadel",     "url": "https://exadel.com"   },
  • Network accessline 7
    "url": "https://exadel.com"
  • Network accessline 19
    "agent-latency"       ],       "homepage": "https://github.com/exadel-inc/agentic-readiness-assessment",
  • Network accessline 20
    ],       "homepage": "https://github.com/exadel-inc/agentic-readiness-assessment",       "repository": "https://github.com/exadel-inc/agentic-readiness-assessment",
  • Network accessline 21
    "homepage": "https://github.com/exadel-inc/agentic-readiness-assessment",
  • Network accessline 22
    "repository": "https://github.com/exadel-inc/agentic-readiness-assessment",
  • Network accessline 24
    "author": {         "name": "Exadel",         "url": "https://exadel.com"
  • Network accessline 25
    "name": "Exadel",         "url": "https://exadel.com"       }
  • Network accessline 26
    "url": "https://exadel.com"

.claude-plugin/plugin.json

  • Network accessline 1
    {   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  • Network accessline 2
    "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  • Network accessline 7
    "author": {     "name": "Exadel",     "url": "https://exadel.com"
  • Network accessline 8
    "name": "Exadel",     "url": "https://exadel.com"   },
  • Network accessline 9
    "url": "https://exadel.com"
  • Network accessline 10
    },   "homepage": "https://github.com/exadel-inc/agentic-readiness-assessment",   "repository": "https://github.com/exadel-inc/agentic-readiness-assessment",
  • Network accessline 11
    "homepage": "https://github.com/exadel-inc/agentic-readiness-assessment",
  • Network accessline 12
    "repository": "https://github.com/exadel-inc/agentic-readiness-assessment",

skills/agent-tool-call-latency/references/CAUSES.md

  • Dangerous shell operationline 91
    `zsh -lc true` takes about 100 ms against about 10 ms for `zsh -c`, and logs that show `/bin/zsh -lc` suggest every command pays it. With shell snapshots on, Codex runs commands in a non-login shell: ask it to run `[[ -o login ]] && echo LO

skills/agent-tool-call-latency/scripts/adapters/antigravity.py

  • Executable scriptline 1
    Executable file

skills/agent-tool-call-latency/scripts/adapters/claude_code.py

  • Executable scriptline 1
    Executable file

skills/agent-tool-call-latency/scripts/adapters/codex.py

  • Executable scriptline 1
    Executable file

skills/agent-tool-call-latency/scripts/adapters/cursor.py

  • Executable scriptline 1
    Executable file

skills/agent-tool-call-latency/scripts/adapters/hooklog.py

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

skills/agent-tool-call-latency/scripts/adapters/t3code.py

  • Executable scriptline 1
    Executable file

skills/agent-tool-call-latency/scripts/aggregate.py

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

skills/agent-tool-call-latency/scripts/common.py

  • Executable scriptline 1
    Executable file
  • Access to secretsline 44
    [Credential-related source omitted]

skills/agent-tool-call-latency/scripts/extract.py

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

skills/agent-tool-call-latency/scripts/hook_capture.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 71
    [Credential-related source omitted]

skills/agent-tool-call-latency/scripts/validate_calls.py

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

skills/agent-tool-call-latency/tests/test_scripts.py

  • Executable scriptline 1
    Executable file
  • Network accessline 82
    def test_redact_masks_a_password_inside_a_url(self):         out = redact("DB=postgresql://app:s3cret@localhost:5432/db psql; git clone https://github.com/a/b")
  • Network accessline 83
    out = redact("DB=postgresql://app:s3cret@localhost:5432/db psql; git clone https://github.com/a/b")
  • Network accessline 84
    self.assertNotIn("s3cret", out)         self.assertIn("postgresql://app:[REDACTED]@localhost", out)         self.assertIn("https://github.com/a/b", out)
  • Network accessline 86
    self.assertIn("https://github.com/a/b", out)
  • Network accessline 93
    [Credential-related source omitted]
  • Network accessline 94
    [Credential-related source omitted]
  • Network accessline 95
    [Credential-related source omitted]
  • Network accessline 96
    [Credential-related source omitted]
  • Network accessline 97
    ("psql --password hunter2 db", "hunter2"),                             ("mysql -u root -phunter2 db", "hunter2"),                             ("curl -u admin:hunter2 https://x", "hunter2"),
  • Network accessline 98
    ("mysql -u root -phunter2 db", "hunter2"),                             ("curl -u admin:hunter2 https://x", "hunter2"),                             ("OPENAI_KEY=abc123 node app.js", "abc123")]:
  • Network accessline 99
    ("curl -u admin:hunter2 https://x", "hunter2"),
  • Access to secretsline 126
    [Credential-related source omitted]
  • Access to secretsline 183
    [Credential-related source omitted]
  • Access to secretsline 233
    [Credential-related source omitted]
  • Access to secretsline 246
    [Credential-related source omitted]
  • Access to secretsline 264
    [Credential-related source omitted]
  • Network accessline 403
    call = dict(kind="shell", command="mkdir -p out && blender -b scene.blend")         self.assertEqual(aggregate.classify(call, patterns), ("Render / 3D", "Blender headless"))         self.assertEqual(aggregate.classify(dict(kind="shell", com
  • Network accessline 404
    self.assertEqual(aggregate.classify(call, patterns), ("Render / 3D", "Blender headless"))         self.assertEqual(aggregate.classify(dict(kind="shell", command="until curl -s x; do sleep 2; done"), patterns),                          ("Wai
  • Network accessline 405
    self.assertEqual(aggregate.classify(dict(kind="shell", command="until curl -s x; do sleep 2; done"), patterns),

skills/agentic-readiness-assessment/scripts/validate_report.py

  • Executable scriptline 1
    Executable file

skills/agentic-readiness-assessment/tests/test_validate_report.py

  • Executable scriptline 1
    Executable file
  • Network accessline 140
    def test_accepts_a_closing_line_after_the_last_section(self) -> None:         closing = "---\n\nThis report covers one repository. See [Exadel](https://exadel.com/)."
  • Network accessline 141
    closing = "---\n\nThis report covers one repository. See [Exadel](https://exadel.com/)."

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: 39 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/agent-tool-call-latency/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/agent-tool-call-latency/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/agent-tool-call-latency/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/agent-tool-call-latency/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/agent-tool-call-latency/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.

You might also use

bladeacer/lccst

Swarming your messy diffs before they reach production.

10GitHub stars

NVIDIA/skills

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

3.9kGitHub stars

foryourhealth111-pixel/Vibe-Skills

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

3.8kGitHub stars

first-fluke/oh-my-agent

Agent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test …

1.4kGitHub stars

scarletkc/agents

Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.

227GitHub stars

supercorp-ai/supercov

Coverage, security and code quality for coding agents

160GitHub stars