agents-reverse-engineer: Skill for Claude Code

.claude/skills/are-discover/SKILL.md

are-discover is a skill for Claude Code from GeoloeG-IsT/agents-reverse-engineer. It costs 9 tokens per session (832 once invoked), scanned A, original, MIT.

A file-discovery workflow that lists the files an agents-reverse-engineer tool will analyze for documentation. The input also specifies how to run and monitor that command.

In plain words
What is it for?
Use it to discover analyzable files in a repository and monitor the command that produces the discovery results.
Why use it?
It helps identify the relevant parts of a codebase before generating documentation or analysis.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: names the AskUserQuestion tool.

This is GeoloeG-IsT/agents-reverse-engineer's own configuration. It tells Claude Code how to work on agents-reverse-engineer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents-reverse-engineer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GeoloeG-IsT/agents-reverse-engineer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GeoloeG-IsT/agents-reverse-engineer/main/.claude/skills/are-discover/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GeoloeG-IsT/agents-reverse-engineer

Made for: Claude Code.

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 are-discover

README.md
[![agentmods](https://agentmods.dev/badge/skills/geoloeg-ist/agents-reverse-engineer/are-discover/github.svg)](https://agentmods.dev/skills/geoloeg-ist/agents-reverse-engineer/are-discover)
Your own site
<a href="https://agentmods.dev/skills/geoloeg-ist/agents-reverse-engineer/are-discover"><img src="https://agentmods.dev/badge/skills/geoloeg-ist/agents-reverse-engineer/are-discover/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for are-discover

Your own site · 80×15
<a href="https://agentmods.dev/skills/geoloeg-ist/agents-reverse-engineer/are-discover"><img src="https://agentmods.dev/badge/skills/geoloeg-ist/agents-reverse-engineer/are-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 832 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 $0.00009 $0.00832
Opus 5 $0.00005 $0.00416
Sonnet 5 $0.00002 $0.00166
Haiku 4.5 $0.00001 $0.00083

Measured 9d ago against content hash 5b55bcbbffc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

are-discover 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 9d 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.

.claude/skills/are-discover/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

List files that would be analyzed for documentation.

  1. Run ONLY this exact command: npx agents-reverse-engineer@$VERSION discover $ARGUMENTS
  2. DO NOT add ANY flags the user did not explicitly type
  3. If user typed nothing after /are-discover, run with ZERO flags

Steps

  1. Read version: Read .claude/ARE-VERSION → store as $VERSION. Show the user: agents-reverse-engineer v$VERSION

  2. Run the discover command in the background using run_in_background: true:

    npx agents-reverse-engineer@$VERSION discover $ARGUMENTS
    
  3. Monitor progress by polling the latest progress log:

    • Wait ~10 seconds (use sleep 10 in Bash), then use Glob to find the latest .agents-reverse-engineer/progress-*.log file, and Read it (use the offset parameter to read only the last ~20 lines for long files)
    • Show the user a brief progress update
    • Check whether the background task has completed using TaskOutput with block: false
    • Repeat until the background task finishes
    • Important: Keep polling even if no progress log exists yet (the command takes a few seconds to start writing)
  4. On completion, read the full background task output and report number of files found.

  5. Review plan and suggest exclusions:

    • Read .agents-reverse-engineer/GENERATION-PLAN.md and .agents-reverse-engineer/config.yaml
    • Scan the Phase 1 file list and classify files into these categories:
      • Test/spec files: matches like *.test.*, *.spec.*, __tests__/**, __mocks__/**, *.stories.*, *.story.*
      • CI/CD configs: .github/workflows/*.yml, .gitlab-ci.yml, Jenkinsfile, .circleci/**, .travis.yml
      • Tool configs: .eslintrc*, .prettierrc*, jest.config.*, .editorconfig, babel.config.*, webpack.config.*, vite.config.*, rollup.config.*, tsconfig*.json, .lintstagedrc*, .huskyrc*, .stylelintrc*, commitlint.config.*
      • Migration files: paths containing migrations/ or matching *.migration.*
      • Fixture/snapshot files: __snapshots__/**, *.fixture.*, fixtures/**, test-data/**, testdata/**
      • Type declarations: *.d.ts (not source code, auto-generated or ambient)
      • Docker/infra: Dockerfile*, docker-compose*, *.Dockerfile, k8s/**, terraform/**, helm/**
    • For each category, count how many files from the plan match and list up to 3 example filenames
    • Skip categories with zero matches — only present categories that have files in the plan
    • Also skip patterns that are already in the current config.yaml exclude list
    • Present the findings in a summary table showing category, file count, example files, and proposed glob patterns
    • Ask the user which categories to exclude using AskUserQuestion with multiSelect: true
    • For accepted categories, use the Edit tool to append the corresponding glob patterns to the exclude.patterns array in .agents-reverse-engineer/config.yaml
    • After editing, briefly confirm what was added

Read the full file on GitHub · 52 lines

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. 9d ago First seen · 52 lines · 9 tokens per session scan A 5b55bcbbffc5

Subscribe to this mod's changes

are-discover is a skill published in the GitHub repository GeoloeG-IsT/agents-reverse-engineer (20 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 832 once invoked, about $0.0000 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 2026-08-30.