Menu

Not in the top 1,000 by GitHub stars

alchemiststudiosDOTai/harness-engineering

harness-engineering discussion of shortcuts, automation, hacks and overall productivity with code agents like claude code, codex, and other harness.

Claude CodeEngineeringProductivity

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/agents-md-mapper/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7a9fa15a4e01

No earlier version was observed for comparison.

Compare on GitHub

skills/ast-grep-setup/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7a9fa15a4e01

No earlier version was observed for comparison.

Compare on GitHub

skills/differential-session-runner/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7a9fa15a4e01

No earlier version was observed for comparison.

Compare on GitHub

skills/execute-phase/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7a9fa15a4e01

No earlier version was observed for comparison.

Compare on GitHub

skills/harness-map/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7a9fa15a4e01

No earlier version was observed for comparison.

Compare on GitHub

skills/plan-phase/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7a9fa15a4e01

No earlier version was observed for comparison.

Compare on GitHub

skills/qa-from-execute/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7a9fa15a4e01

No earlier version was observed for comparison.

Compare on GitHub

skills/research-phase/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7a9fa15a4e01

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 7a9fa15a4e018c8e26dbf01b9e1c5bdcabd56d72

git clone --filter=blob:none --no-checkout https://github.com/alchemiststudiosDOTai/harness-engineering.git .hotskills/alchemiststudiosdotai-harness-engineering && git -C .hotskills/alchemiststudiosdotai-harness-engineering checkout --detach 7a9fa15a4e018c8e26dbf01b9e1c5bdcabd56d72 # Copy each selected skill directory from .hotskills/alchemiststudiosdotai-harness-engineering into .claude/skills/<skill-name>/
105GitHub stars
0stars in 7 days
8skills in this repository
0commits in 30 days

Heat

0.3
  • 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 25, 2026105

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

Individual skills in this repository

How it works

agents-md-mapper

When your agent uses it

This skill should be used when creating, refreshing, or validating a repository `AGENTS.md` so it stays concise, current, and grounded in repository evidence. Use when `AGENTS.md` is missing or stale, after refactors or tooling changes, when new docs become the system of record, or when adding lightweight drift checks.

What it loads into context

Frontmatter

208 tokens

Always available to the agent

SKILL.md

1,559 tokens

When the skill is activated

Reference documents

299 tokens

Loaded on request

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

The playbook

  1. Overview
  2. When to Use
  3. Core Contract
  4. Inputs to Inspect
  5. Workflow
  6. What to Put in `AGENTS.md`
  7. Decision Rules
  8. Output Modes
  9. Validation Checklist
  10. Recommended Follow-Up Checks
  11. Success Criteria

Files

  • ../../.claude-plugin/plugin.jsonasset614 bytes
  • ../../prompt-hooks/examples/plugin/hooks.jsonasset460 bytes
  • ../../prompt-hooks/examples/plugin/hooks.jsonasset460 bytes
  • SKILL.mdcore7,268 bytes
  • SKILL.mdcore7,268 bytes
  • SKILL.mdcore7,268 bytes
  • SKILL.mdcore7,268 bytes
  • SKILL.mdcore7,268 bytes
  • SKILL.mdcore7,268 bytes
  • references/agents-md-outline.mddoc1,249 bytes
Read SKILL.md

# AGENTS.md Mapper

## Overview

Maintain a concise, current `AGENTS.md` for a repository as the codebase changes. Treat the file as a navigational map for future coding agents: show where to start, where important things live, how to validate changes, and which deeper docs outrank the map.

## When to Use

- Create a new `AGENTS.md` for a repository that does not have one
- Refresh an existing `AGENTS.md` that may be stale after refactors, path moves, package splits, or architecture changes
- Update the map after tooling, tests, CI, docs, or ownership signals changed
- Point `AGENTS.md` at new architecture docs, runbooks, or generated references that became the source of truth
- Add lightweight checks that detect drift between `AGENTS.md` and repository reality
View the complete source on GitHub

Skills included

  • agents-md-mapper
  • ast-grep-setup
  • differential-session-runner
  • execute-phase
  • harness-map
  • plan-phase
  • qa-from-execute
  • research-phase

Repository facts

License
MIT
Created
Jul 25, 2025
Last pushed
Mar 17, 2026
Forks
13
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

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

Show 49 notes
  • prompt-hooks/examples/plugin/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/agents-md-mapper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/agents-md-mapper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/agents-md-mapper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/agents-md-mapper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/agents-md-mapper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ast-grep-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/differential-session-runner/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/execute-phase/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/execute-phase/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/execute-phase/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 58 signals by file

.claude-plugin/plugin.json

  • Network accessline 6
    "name": "Harness Engineering"   },   "repository": "https://github.com/alchemiststudiosDOTai/harness-engineering",
  • Network accessline 7
    },   "repository": "https://github.com/alchemiststudiosDOTai/harness-engineering",   "license": "MIT",
  • Network accessline 8
    "repository": "https://github.com/alchemiststudiosDOTai/harness-engineering",

skills/agents-md-mapper/SKILL.md

  • Broad permissionsline 1
    Bash(git:*)

skills/ast-grep-setup/SKILL.md

  • Network accessline 423
    valid:   - |     const result = await fetch('/api/users');
  • Network accessline 424
    - |     const result = await fetch('/api/users');   - |
  • Network accessline 425
    const result = await fetch('/api/users');
  • Network accessline 426
    - |     return fetch('/api/users');   - |
  • Network accessline 427
    return fetch('/api/users');
  • Network accessline 428
    - |     fetch('/api/users').catch(err => console.error(err));   - |
  • Network accessline 429
    fetch('/api/users').catch(err => console.error(err));
  • Network accessline 431
    new Promise((resolve) => setTimeout(resolve, 1000));   - |     Promise.all([fetch('/a'), fetch('/b')]);
  • Network accessline 432
    - |     Promise.all([fetch('/a'), fetch('/b')]); invalid:
  • Network accessline 433
    Promise.all([fetch('/a'), fetch('/b')]);
  • Network accessline 435
    - |     function getUsers() {       fetch('/api/users');
  • Network accessline 436
    function getUsers() {       fetch('/api/users');     }
  • Network accessline 437
    fetch('/api/users');
  • Network accessline 439
    - |     async function load() {       fetch('/api/data');
  • Network accessline 440
    async function load() {       fetch('/api/data');     }
  • Network accessline 441
    fetch('/api/data');
  • Network accessline 581
    rule:   any:     - pattern: fetch($$$)
  • Network accessline 582
    any:     - pattern: fetch($$$)     - pattern: axios.$METHOD($$$)
  • Network accessline 583
    - pattern: fetch($$$)

skills/ast-grep-setup/scripts/validate-rule.py

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

skills/ast-grep-setup/templates/rule-tests/no-floating-promises-test.yml

  • Network accessline 2
    valid:   - |     const result = await fetch('/api/users');
  • Network accessline 3
    - |     const result = await fetch('/api/users');   - |
  • Network accessline 4
    const result = await fetch('/api/users');
  • Network accessline 5
    - |     return fetch('/api/users');   - |
  • Network accessline 6
    return fetch('/api/users');
  • Network accessline 7
    - |     fetch('/api/users').catch(err => console.error(err));   - |
  • Network accessline 8
    fetch('/api/users').catch(err => console.error(err));
  • Network accessline 10
    new Promise((resolve) => setTimeout(resolve, 1000));   - |     Promise.all([fetch('/a'), fetch('/b')]);
  • Network accessline 11
    - |     Promise.all([fetch('/a'), fetch('/b')]);   - |
  • Network accessline 12
    Promise.all([fetch('/a'), fetch('/b')]);
  • Network accessline 13
    - |     async function load() {       return await fetch('/data');
  • Network accessline 14
    async function load() {       return await fetch('/data');     }
  • Network accessline 15
    return await fetch('/data');
  • Network accessline 18
    - |     function getUsers() {       fetch('/api/users');
  • Network accessline 19
    function getUsers() {       fetch('/api/users');     }
  • Network accessline 20
    fetch('/api/users');
  • Network accessline 22
    - |     async function load() {       fetch('/api/data');
  • Network accessline 23
    async function load() {       fetch('/api/data');     }
  • Network accessline 24
    fetch('/api/data');

skills/differential-session-runner/SKILL.md

skills/execute-phase/SKILL.md

  • Broad permissionsline 1
    Bash(git:*)
  • Access to secretsline 277
    [Credential-related source omitted]

skills/harness-map/SKILL.md

  • Broad permissionsline 1
    Bash(find:*)

skills/plan-phase/SKILL.md

  • Broad permissionsline 1
    Bash(git:*)
  • Network accessline 159
    - Create src/middleware/auth.ts with verifyToken() function - Import in src/app.ts and apply to /api/* routes - Acceptance: curl /api/users returns 401 without header, 200 with valid token
  • Network accessline 160
    - Import in src/app.ts and apply to /api/* routes - Acceptance: curl /api/users returns 401 without header, 200 with valid token - Files: src/middleware/auth.ts, src/app.ts
  • Network accessline 161
    - Acceptance: curl /api/users returns 401 without header, 200 with valid token

skills/qa-from-execute/SKILL.md

skills/research-phase/SKILL.md

skills/research-phase/scripts/ast-scan.sh

  • Executable scriptline 1
    #!/bin/bash

skills/research-phase/scripts/dependency-graph.sh

  • Executable scriptline 1
    #!/bin/bash

skills/research-phase/scripts/structure-map.sh

  • Executable scriptline 1
    #!/bin/bash
  • Access to secretsline 48
    [Credential-related source omitted]

skills/research-phase/scripts/symbol-index.sh

  • Executable scriptline 1
    #!/bin/bash

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: 36 facts

Works with

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

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

316.4kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.5kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.1kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230.2kGitHub stars

anthropics/skills

Public repository for Agent Skills

188.1kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

185.7kGitHub stars