agentleFS
Sign inStart free
GstMirabalGstMirabal/Token-Optimized-Agent-Pipeline/skills/compliance-checker/SKILL.md

compliance-checker

Skill1 starsChanged 11 days agoMITView on GitHub

Compliance engine that scans plans, roadmaps, and code for governance rule violations before they reach execution, and synthesizes rule amendments to agents.md from recurring friction found in /memory/ logs.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ad-copy.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • brainbytes-devSkill

    ad-copy

    Write high-performing ad copy for Google, Meta, LinkedIn, and TikTok. Use when creating paid advertising creative.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    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. Very specific:

    Halt Trigger: If a violation is found in an implementation_plan.md, the agent must throw a HALT state and provide a specific …

    line 21
  2. Very specific:

    Coordinate Audit: Verify that active_state.json is healthy and that its current_sprint_id matches the task headers.

    line 29
  3. Distinctive:

    Language Guard: All audit reports and amendment proposals MUST be in Technical English.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

🛠️ Local Skill: Compliance Checker (v1.0.0)

Domain

  • Category: Governance / Quality Assurance / Compliance
  • Origin: Custom synthesis for automated governance rule auditing.
  • Status: ACTIVE_LOCAL
  • Sovereignty: local (Project-Specific)

Technical Logic

This skill provides the Compliance Engine for the framework. It enables a subagent to proactively scan workspace artifacts (plans, roadmaps, code) to detect and block governance rule violations before they reach the execution phase.

Procedures

1. Compliance Scanning (Pre-Execution Audit)

  • Restricted Pattern Detection: Scan for "Negative Restrictions" defined in agents.md (e.g., absolute paths, Spanish in code, global variable injections).
  • Halt Trigger: If a violation is found in an implementation_plan.md, the agent must throw a HALT state and provide a specific logic-violation report.

2. Pattern Synthesis (Rule Amendments)

  • Friction Extraction: Analyze /memory/ logs to identify recurring technical friction or workflow bottlenecks.
  • Amendment Draft: Propose formal amendments to agents.md formulated as technical clauses that provide a definitive solution to the identified friction.
  • Automation: scripts/distill.py runs frequency analysis over memory/telemetry/raw_errors.json and drafts proposal clauses; scripts/apply_rule_amendments.py parses approved clauses from memory/telemetry/proposals.md into agents.md Section 7. Both require explicit human approval before any write to agents.md.

3. State Integrity Verification

  • Coordinate Audit: Verify that active_state.json is healthy and that its current_sprint_id matches the task headers.

Governance Audit

  • Sovereignty Policy: This skill has final authority on code compliance; its findings must be respected by all Dev and Orchestration nodes.
  • Language Guard: All audit reports and amendment proposals MUST be in Technical English.

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