Agents Md
This audits your AGENTS.md files against execution-first standards, checking whether commands are stale, rules are bloated, or gotchas are actually grounded in real failures. Default mode runs a quick 10-point checklist targeting 8/10, escalating to full audit only when needed. It'll catch the usual suspects: dead links, generic "follow best practices" fluff, missing test commands, and hypothetical warnings that agents learn to ignore. The core insight is solid: every line should prevent a mistake or get cut, because bloated instruction files train agents to skip the rules that matter. Use it when your agent keeps ignoring critical setup steps or when your instructions have grown past 150 lines without anyone noticing.
- skills.sh installs
- 884
- GitHub stars
- 191
- last updated
- Aug 21, 2026
Install
$ npx -y skills add mblode/agent-skills --skill agents-md --agent claude-codeInstalls into .claude/skills of the current project.
Files
AGENTS.md Setup and Audit
- IS: wiring a repo so every agent tool in use reads the same rules, then auditing, scoring, refactoring, and writing the AGENTS.md / CLAUDE.md / CLAUDE.local.md files agents load at session start.
- IS NOT: authoring SKILL.md files (use
agent-skills-creator), project docs or READMEs (useghostwriter), or mining session history (use the externalcadence-adviseskill where installed; this skill audits the file as-is).
AGENTS.md files are execution contracts, not knowledge bases. Two tests catch the two ways a line fails.
- Dead weight: "Would removing this cause the agent to make a mistake?" If no, cut it; bloat makes agents ignore the rules that matter.
- Harmful precision: "Is this wrong on any plausible task in this repo?" A prohibition that is wrong one task in ten is still obeyed on that task, and the agent cannot tell that this is the exception. State the outcome you want and let the surrounding code pick the path.
NEVER write commentsbecomesmatch the comment density of the file you are editing: shorter, no exception list to maintain, and correct in a densely commented file without being told.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/mblode/agent-skills
- Categories
- Git & Pull Requests, Documentation, Code Review & Quality, AI & Agent Building, Debugging
- First seen
- Jun 3, 2026
More from mblode/agent-skills
All 22- Scaffold Nextjs785
- Scaffold Cli751
- Ui Audit733
- Autoship687
- Optimise Seo647
- Readme Creator604
- Copywriting483
- Define Architecture448
- Blog Post404
- Review Pr185
- Agent Native140
- Babysit Pr124
- Mermaid Mind Map124
- Audit Ui114
- Ui Animation10.8K
- Multi Tenant Architecture1.8K
- Ui Design1.5K
- Typography Audit1.1K
- Agent Skills Creator1K
- Presentation Creator960
- Docs Writing949
Recommended
More Git & Pull Requests
d3kvercel-labs/dev3000Use when the user asks to use d3k, run/dev/test/debug a web project with d3k, or reproduce a browser issue. Own the runtime: reuse or background-start d3k non-i877skills.sh installs
solidity-auditorpashov/skillsSecurity audit of Solidity code while you develop. Trigger on "audit", "check this contract", "review for security". Modes - default (full repo) or a specific f874skills.sh installs
webgpucazala/webgpu-skillDesign, implement, debug, review, and optimize portable WebGPU applications and WGSL shaders. Use when building render or compute pipelines; GPU simulations, ce873skills.sh installs
python-best-practicesnathan-gage/python-skillsPython software engineering guidelines from real PR review patterns. This skill should be used when writing, reviewing, or refactoring Python code — especially 868skills.sh installs
adversarial-revieweralirezarezvani/claude-skillsAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when y856skills.sh installs
jirasoftaworks/agent-toolkitUse when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira wor854skills.sh installs