agents-md-revise

agents-md-revise is a skill for Claude Code from shrekshrek/project-workflow. It costs 30 tokens per session (279 once invoked), scanned A, original, MIT.

A procedure for updating AGENTS.md files, which contain instructions for coding agents, so they match the project's actual conventions. It compares the written rules with the repository and applies only approved corrections.

In plain words
What is it for?
It helps refresh project guidance, review convention drift, audit where instructions belong, and report which changes were applied, skipped, or left unresolved.
Why use it?
It finds outdated or misplaced agent instructions without changing product code or specifications. It also checks proposed guidance changes against the project's documented rules and current state.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions AGENTS.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the project-workflow plugin — 9 skills, 6 agents shipped together

Good fit It helps refresh project guidance, review convention drift, audit where instructions belong, and report which changes were applied, skipped, or left unresolved.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add shrekshrek/project-workflow
Claude Code
/plugin install project-workflow

Made for: Claude Code.

Or install project-workflow, the plugin that ships this one along with the rest of its 9 skills, 6 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agents-md-revise

README.md
[![agentmods](https://agentmods.dev/badge/skills/shrekshrek/project-workflow/agents-md-revise.svg)](https://agentmods.dev/skills/shrekshrek/project-workflow/agents-md-revise)
Your own site
<a href="https://agentmods.dev/skills/shrekshrek/project-workflow/agents-md-revise"><img src="https://agentmods.dev/badge/skills/shrekshrek/project-workflow/agents-md-revise.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00279
Opus 5 $0.00015 $0.00139
Sonnet 5 $0.00006 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 8d ago against content hash 200d807e29e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agents-md-revise scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

adapters/claude/skills/agents-md-revise/SKILL.md · 21 lines

What it actually says

Agents.md Revise

Match the user's language. Read ${CLAUDE_PLUGIN_ROOT}/docs/actions/agents-md-revise.md completely before acting; it owns the portable workflow and contract.

Claude execution details:

  • Parse $ARGUMENTS as an optional scope. Root/applicable nested AGENTS.md are the default; include .claude/rules/ only when the user explicitly selects them.
  • Use Read/Grep/Glob/Bash for evidence. Missing AGENTS.md redirects to /project-workflow:project-personalize.
  • Use inline trace for sourced synchronization; dispatch a fresh decision-completeness-auditor only at its narrowed canonical boundary, with fallback under the shared execution contract. Blocking or unreliable audit evidence prevents apply.
  • Ask only for material ambiguity or new policy; do not reconfirm objective stale-value synchronization item by item.
  • Run the canonical Guidance Placement audit and apply only evidence-backed placement changes.
  • Apply only convention edits authorized by the current request or an explicit follow-up decision. Do not edit product specs, implementation code, or commit.

Report applied/skipped drift, evidence, applicable audit execution/results, and unresolved questions.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 21 lines · 30 tokens per session scan A 200d807e29e4

Subscribe to this mod's changes

agents-md-revise is a skill published in the GitHub repository shrekshrek/project-workflow (2 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 279 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

improve

Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.

SethGammon/Citadel · 48 tokens

evolve

Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…

SethGammon/Citadel · 60 tokens

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens