agents-reverse-engineer: Skill for Claude Code

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

are-plan is a skill for Claude Code from GeoloeG-IsT/agents-reverse-engineer. It costs 15 tokens per session (386 once invoked), scanned A, original, MIT.

A planning comparison workflow runs an AI planner with and without project documentation, then measures the difference. It checks details such as referenced files, actionable steps, code identifiers, cost, timing, and optional quality scores.

In plain words
What is it for?
Use it to compare two planning runs, evaluate their quality, and inspect the effect of documentation before implementation.
Why use it?
It shows whether documentation makes implementation plans more specific and useful.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

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-plan/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-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/geoloeg-ist/agents-reverse-engineer/are-plan.svg)](https://agentmods.dev/skills/geoloeg-ist/agents-reverse-engineer/are-plan)
Your own site
<a href="https://agentmods.dev/skills/geoloeg-ist/agents-reverse-engineer/are-plan"><img src="https://agentmods.dev/badge/skills/geoloeg-ist/agents-reverse-engineer/are-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 386 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 $0.00015 $0.00386
Opus 5 $0.00008 $0.00193
Sonnet 5 $0.00003 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 8d ago against content hash 0e5cf71daa34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

are-plan 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.

.claude/skills/are-plan/SKILL.md · 44 lines

What it actually says

Compare AI planning quality with and without ARE documentation.

Steps

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

  2. Run the plan command:

    npx agents-reverse-engineer@$VERSION plan --backend claude $ARGUMENTS
    
  3. Wait for completion — the command runs two sequential AI planning sessions (without docs, then with docs) and outputs a comparison table.

  4. On completion, summarize the comparison results:

    • Quantitative metrics (file references, actionable steps, code identifiers)
    • Cost and latency comparison
    • Quality evaluation scores (if --eval was used)

This creates two git branches from HEAD and runs an AI planner in each:

  • With ARE docs: Full documentation available
  • Without ARE docs: Source code only (ARE artifacts stripped)

The comparison measures how much ARE documentation improves AI planning quality.

Options:

  • --eval: Run AI quality evaluator on both plans (5-point rubric)
  • --eval-model <name>: Model for the evaluator (default: same as --model)
  • --model <name>: AI model to use for planning
  • --dry-run: Show what would happen without executing
  • --list: List all saved plan comparisons
  • --show <id>: View a previous comparison by date
  • --force: Overwrite existing branches for the same task
  • --debug: Show verbose AI execution details
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 · 44 lines · 15 tokens per session scan A 0e5cf71daa34

Subscribe to this mod's changes

are-plan is a skill published in the GitHub repository GeoloeG-IsT/agents-reverse-engineer (20 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 386 once invoked, about $0.0001 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.