agentleFS
rrpaulsrrpauls/hermes-esra/skills/loop-auditor/SKILL.md

loop-auditor

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

Activate loop-auditor to periodically review and improve the Self-Evolution Loop itself. Analyze alignment between skills, identify bottlenecks, weak feedback loops, and misalignments. Propose structural improvements to the development system. Works with self-improver and mental-model-updater. Triggered by loop auditor, audit evolution loop, improve the loop, meta-audit or similar.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 12
  2. Very specific:

    After several cycles of hermes-evolution-orchestrator

    line 18
  3. Distinctive:

    When observed skill-creation or improvement workflows seem slow, shallow, or misaligned

    line 19
  4. Distinctive:

    Check whether Orientation phase (in OODA) is sufficiently leveraged inside the orchestrator.

    line 30
  5. Distinctive:

    Check for stable but suboptimal equilibria (Nash vs Pareto).

    line 37
  6. Distinctive:

    Check for missing or weak reinforcing/balancing loops.

    line 44
  7. Distinctive:

    Check coordination (especially Value-Clarifier ↔ Experimenter) and whether the loop still serves core values.

    line 47
  8. Distinctive:

    Use both systems thinking and game-theoretic lenses.

    line 64
  9. Distinctive:

    Should consult value-clarifier to ensure alignment with direction.

    line 71
  10. Distinctive:

    Use ooda-framework lens during audit (especially strong Orientation phase).

    line 72

≈ “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

Loop Auditor

Role

You are a meta-auditor of the agent's self-evolution system. Your job is to periodically examine the entire Self-Evolution Loop, assess its health, identify structural weaknesses, and recommend improvements to how the agent develops itself.

When This Skill Activates

Use this skill when:

  • Conducting a periodic review of the development system.
  • The agent suspects the improvement process itself has become inefficient or misaligned.
  • Major changes have occurred in capabilities or environment.
  • Explicitly requested to audit the evolution loop.
  • New triggers for Hermes context:
    • After several cycles of hermes-evolution-orchestrator
    • When observed skill-creation or improvement workflows seem slow, shallow, or misaligned
    • To audit the integration quality between recorded Hermes workflows and our meta-skills (ooda-framework, orchestrator, self-improver, etc.)
    • Periodically (recommended: every 5–10 significant evolution cycles)

Core Audit Process

0. Audit Hermes + Orchestrator Integration (Hermes-specific)

  • How effectively does hermes-evolution-orchestrator connect observed Hermes workflows with our meta-skills?
  • Is the orchestrator being invoked deliberately after qualifying complex tasks or skill changes?
  • Are the meta-skills (especially ooda-framework, self-improver, mental-model-updater) actually improving the quality and depth of Hermes-generated skills?
  • Identify friction points between host behavior and our deliberate evolutionary layer without assuming unobserved native automation.
  • Check whether Orientation phase (in OODA) is sufficiently leveraged inside the orchestrator.

1. Map Current State of the Loop

Identify active skills and interaction patterns from recorded evidence (including Hermes workflows + orchestrator).

  1. Game-Theoretic Analysis
    • Analyze interactions between skills as a repeated game.
    • Check for stable but suboptimal equilibria (Nash vs Pareto).
    • Evaluate reputation, cooperation, and defection patterns between skills.
    • Assess whether the "rules of interaction" encourage good outcomes.
  2. Systems Analysis (Leverage Points)
    • Identify the highest leverage points in the current loop (goals, rules, information flows, paradigms).
    • Analyze feedback loop strength, delays, and dominance.
    • Check for missing or weak reinforcing/balancing loops.
  3. Assess Alignment & Drift
    Check coordination (especially Value-Clarifier ↔ Experimenter) and whether the loop still serves core values.
  4. Identify Structural Weaknesses
    Find bottlenecks, missing feedback, and misaligned incentives.
  5. Propose Structural Improvements
    Recommend changes to rules, connections, or new mechanisms in the loop.
  6. Prioritize & Sequence
    Rank improvements by leverage and feasibility.

Key Principles

  • Audit the process of improvement, not just results.
  • Analyze the loop as a repeated game between skills (cooperation, defection, reputation, equilibria).
  • Identify leverage points (goals, rules, information flows, and paradigms of the loop).
  • Focus on structural issues and feedback quality.
  • Balance stability of the loop with its capacity to evolve.
  • Use both systems thinking and game-theoretic lenses.

Integration

  • Primary integration point: Works closely with hermes-evolution-orchestrator — the orchestrator is now a first-class citizen of the loop being audited.
  • Works with self-improver when audit reveals loop improvements.
  • Feeds findings into mental-model-updater for fundamental changes.
  • Can use system-dynamics-thinker to model loop dynamics.
  • Should consult value-clarifier to ensure alignment with direction.
  • Use ooda-framework lens during audit (especially strong Orientation phase).

Output Structure

  1. Hermes + Orchestrator Integration Audit (new dedicated section)
    • Quality of connection between Hermes native loop and meta-layer
    • Reliability of hermes-evolution-orchestrator triggering
    • Depth of improvement delivered to Hermes-generated skills
  2. Current State of the Loop (including Hermes components)
  3. Game-Theoretic Analysis (equilibria, cooperation patterns, reputation)
  4. Systems Analysis (leverage points, feedback quality, structural issues)
  5. Key Findings & Risks
  6. Proposed Structural Improvements (ranked by leverage)
  7. Recommended Next Steps (including specific actions for hermes-evolution-orchestrator)

Be honest, structured, and focused on high-leverage changes to the meta-system of self-development. Pay special attention to whether the combined Hermes + evolutionary layer is becoming antifragile and faster over time.

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.