agentleFS
Sign inStart free
lorenzofamiglinilorenzofamiglini/The-Forge-Protocol-Agent/skills/forge-audit/SKILL.md

forge-audit

Skill15 starsChanged 7 months agoMITView on GitHub

Run Forge Protocol self-audits — weekly canary, monthly stress test, or quarterly dependency review.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Dshamir/slm-forge★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Test your unassisted skills to prevent AI dependency from eroding your capabilities.

    line 15
  2. Very specific:

    Call forge_get_state to check audit status and which audits are overdue.

    line 45
  3. Very specific:

    Quarterly dependency audit: call forge_dependency_report — this computes mode-usage ratios across every session, total violations, and a …

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Forge Audit — Self-Assessment System

Test your unassisted skills to prevent AI dependency from eroding your capabilities.

Audit Types

Weekly Canary (/forge-audit weekly)

A timed challenge you complete without AI assistance:

  • A fixed set of writing, analysis, debugging, strategy, and communication prompts (stable IDs so you take the same one repeatedly)
  • 5-10 minute time limit
  • Your answer is scored by an independent Claude Sonnet auditor on clarity, depth, and independence
  • Scores are stored across weeks — you see trend, change vs. previous, mean of last 5, linear slope
  • Purpose: measure, not just remind. If your independence score drifts down, the canary catches it before you do.

Monthly Stress Test (/forge-audit monthly)

A harder challenge requiring sustained unassisted work:

  • Complete a significant task without AI for 30-60 minutes
  • Compare output quality to your AI-assisted baseline
  • Purpose: verify you can still perform under pressure

Quarterly Dependency Audit (/forge-audit quarterly)

Review your AI usage patterns across all sessions:

  • Mode ratios (are you living in Executor mode?)
  • Violation trends (is the AI breaking mode rules more often?)
  • Skill progression (are canary scores improving or declining?)
  • Purpose: macro-level view of your cognitive sovereignty

How It Works

  1. Call forge_get_state to check audit status and which audits are overdue.
  2. Weekly canary: call forge_canary_list to show the user the fixed prompts (or pick one by id), present the challenge, enforce the time limit by prompting the user to commit before submitting. Submit the response via forge_canary_submit(prompt_id, response) — the adversarial auditor (Claude Sonnet) scores it and returns the full trend. Show the user their last score, change vs. previous, and slope across attempts; be honest about what the data says.
  3. Quarterly dependency audit: call forge_dependency_report — this computes mode-usage ratios across every session, total violations, and a health assessment ("WARNING: 80% in Executor mode…" or "Healthy balance…"). It also records the audit-completion timestamp so the overdue reminder clears.
  4. Monthly stress test: there is no dedicated tool — present an unassisted 30–60 minute challenge, then log the outcome conversationally.

Healthy Targets

  • Mode split: ~40% Forge/Crucible, ~30% Anvil, ~30% Executor
  • Canary trend: stable or improving over 4+ weeks
  • Violation rate: decreasing over time (AI learning to stay in mode)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free