metacognitive-self-mod SKILL.md skillA

metacognitive-self-mod from athola/claude-night-market is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add athola/claude-night-market/metacognitive-self-mod@git:20260813.0bee82e

Pins git:20260813.0bee82e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
athola/claude-night-market
Path
plugins/abstract/skills/metacognitive-self-mod/SKILL.md
Versions recorded
5
Latest version
git:20260813.0bee82e, committed Aug 13, 2026
First version recorded
May 29, 2026
Size
8,898 bytes
Repository stars
348
License
MIT

Analyze and improve the improvement process. Use for detecting regressions and meta-optimization.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Metacognitive Self-Modification

## Overview

Analyze the effectiveness of past skill improvements and
refine the improvement process itself. This is the core
innovation from the Hyperagents paper: not just improving
skills, but improving HOW skills are improved.

## Context Triggers (auto-invocation)

This skill should be invoked automatically when:

1. **Regression detected**: The homeostatic monitor finds
   a skill's evaluation window ended in
   `pending_rollback_review` status. The improvement
   made things worse, and we need to understand why.

2. **Low effectiveness rate**: When
   `ImprovementMemory.get_effective_strategies()` vs
   `get_failed_strategies()` shows effectiveness below
   50%, the improvement process itself needs refinement.

3. **Degradation despite improvements**: When
   `PerformanceTracker.get_improvement_trend()` returns
   negative for a skill that was recently improved.

4. **Periodic check**: After every 10 improvement cycles
   (tracked via outcome count in ImprovementMemory).

### Hook integration

The homeostatic monitor emits
`"improvement_triggered": true` when a skill crosses the
flag threshold. At that point, before dispatching the
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add athola/claude-night-market/metacognitive-self-mod@sha256:709399359d2de90c

The line at the top of this page pins the label git:20260813.0bee82e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_sxau3cowrrewu3ol.svg)](https://markdownregistry.com/a/art_sxau3cowrrewu3ol)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between May 29, 2026 and Aug 13, 2026, about one every 19 days.

versioncommittedcommitsizeaudit
git:20260813.0bee82e latest2026-08-13 0bee82e 8,898 BA view · diff
git:20260726.e7e9ab82026-07-26 e7e9ab8 8,902 BA view · diff
git:20260622.63c6c162026-06-22 63c6c16 8,867 BA view · diff
git:20260601.8d672122026-06-01 8d67212 8,170 BA view · diff
git:20260529.62f598e2026-05-29 62f598e 8,169 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8898 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

athola/claude-night-market · 348 stars · license MIT · pushed 2026-11-05 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_sxau3cowrrewu3ol
GET https://markdownregistry.com/api/v1/resolve?ref=athola/claude-night-market/metacognitive-self-mod
GET https://markdownregistry.com/api/v1/blob/709399359d2de90c944c452994299fdb1479ca25bb08365ffc0b4717690b4ff3

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from athola/claude-night-market

claude-code-plugin-reference SKILL.md skill
athola/claude-night-market · .claude/skills/claude-code-plugin-reference/SKILL.md · Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not…
git:20261005.d8ad765 · audit A · 348 stars
night-market-architecture-contract SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-architecture-contract/SKILL.md · States load-bearing decisions, invariants, and weak points. Use when judging a design change. Do not use for gating…
git:20260826.3466862 · audit A · 348 stars
night-market-build-and-env SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-build-and-env/SKILL.md · Rebuild the dev environment: uv, Python tiers, pins, traps. Use when onboarding or toolchain breaks. Do not use for…
git:20260903.255430d · audit A · 348 stars
night-market-change-control SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-change-control/SKILL.md · Classify, gate, and review changes. Use when landing a PR, releasing, or amending rules. Do not use for failure triage…
git:20260703.19ab4d6 · audit A · 348 stars
night-market-collective-memory SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-collective-memory/SKILL.md · Search and record project memory (Discussions, journal, ADRs). Use before re-investigating anything. Do not use for…
git:20260703.19ab4d6 · audit A · 348 stars
night-market-completion-integrity-campaign SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-completion-integrity-campaign/SKILL.md · Bind loop 'done' to unfakeable gates. Use to harden egregore/herald loops or promote completion_integrity. Not for QA…
git:20261005.fe60b22 · audit A · 348 stars
night-market-config-catalog SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-config-catalog/SKILL.md · Catalog every config axis, its defaults and guards. Use when adding or auditing configuration. Do not use for running…
git:20261014.ccfbdae · audit A · 348 stars
night-market-debugging-playbook SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-debugging-playbook/SKILL.md · Triage night-market failures by symptom (hooks, CI, tests). Use when a check fails unexpectedly. Do not use for routine…
git:20260703.19ab4d6 · audit A · 348 stars
night-market-diagnostics-toolkit SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-diagnostics-toolkit/SKILL.md · Run and interpret repo diagnostic scripts (ratchets, validators, token stats). Use when measuring health. Do not use to…
git:20261005.4c9e340 · audit A · 348 stars
night-market-docs-and-writing SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-docs-and-writing/SKILL.md · Maintain docs of record, ADRs, changelog, and house style. Use when writing repo docs. Do not use for release steps…
git:20260902.b3bb3ff · audit A · 348 stars
night-market-failure-archaeology SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-failure-archaeology/SKILL.md · Chronicles settled battles, reverts, and dead ends. Use when a fix echoes a past failure. Do not use for live triage…
git:20260703.19ab4d6 · audit A · 348 stars
night-market-model-and-harness-updates SKILL.md skill
athola/claude-night-market · .claude/skills/night-market-model-and-harness-updates/SKILL.md · Sweep plugins, skills, agents, commands, and hooks after a model release or Claude Code version bump. Use when upstream…
git:20260814.0f2ecb7 · audit A · 348 stars

Every file in athola/claude-night-market

Browse by kind, by grade A, or by owner.