metacognition SKILL.md skillA

metacognition from shinpr/agentic-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add shinpr/agentic-code/metacognition@git:20261103.998947c

Pins git:20261103.998947c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
shinpr/agentic-code
Path
.agents/skills/metacognition/SKILL.md
Versions recorded
5
Latest version
git:20261103.998947c, committed Nov 3, 2026
First version recorded
Dec 30, 2025
Size
2,912 bytes
Repository stars
51
License
MIT

Checks task understanding, evidence, scope, and stopping conditions at decision-changing moments. Use when starting repository work, changing task type, encountering unexpected evidence, or completing a meaningful phase.

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

# Metacognition Protocol

## Purpose

Prevent the agent from following an invalid route, expanding work without evidence, or declaring completion without observable proof.

## Checkpoints

Run a checkpoint when:

- repository work begins;
- the task type or the requested outcome changes;
- unexpected evidence invalidates the current approach;
- a major phase or coherent implementation task completes;
- the next action requires user authority or an irreversible operation.

Routine reversible actions inside an already validated approach do not require a separate checkpoint.

## Assessment

### Outcome and Scope

- What observable outcome owns this work?
- Which requirements are current, and which items are current-state evidence or speculation?
- What non-goals and contracts must remain unchanged?
- Could reuse or no-change already satisfy the outcome?

### Evidence

- Which claims are observed, inferred, or unknown?
- What repository rule or pattern governs the next decision?
- Does an unknown change the outcome, scale, major design, authority, or verification?

### Approach

- Is the current route the smallest sufficient one?
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add shinpr/agentic-code/metacognition@sha256:b617b6a3753a7522

The line at the top of this page pins the label git:20261103.998947c, 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_p3p6h7zdmde6omra.svg)](https://markdownregistry.com/a/art_p3p6h7zdmde6omra)

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

Versions

The registry has recorded 5 versions of this file, between Dec 30, 2025 and Nov 3, 2026, about one every 77 days.

versioncommittedcommitsizeaudit
git:20261103.998947c latest2026-11-03 998947c 2,912 BA view · diff
git:20260829.876a2142026-08-29 876a214 2,922 BA view · diff
git:20251231.cb53cf62025-12-31 cb53cf6 5,414 BA view · diff
git:20251230.9a88ee82025-12-30 9a88ee8 5,487 BA view · diff
git:20251230.7fa7e692025-12-30 7fa7e69 5,487 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 (2912 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

shinpr/agentic-code · 51 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_p3p6h7zdmde6omra
GET https://markdownregistry.com/api/v1/resolve?ref=shinpr/agentic-code/metacognition
GET https://markdownregistry.com/api/v1/blob/b617b6a3753a7522c2b58acc4901dd4c43fe6a5fc922c0aea68937c84559aac2

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 shinpr/agentic-code

ai-development-guide SKILL.md skill
shinpr/agentic-code · .agents/skills/ai-development-guide/SKILL.md · Applies root-cause analysis, impact inspection, and completeness checks without expanding the requested scope. Use when…
git:20261103.998947c · audit A · 51 stars
coding-rules SKILL.md skill
shinpr/agentic-code · .agents/skills/coding-rules/SKILL.md · Applies repository-aware rules for maintainable implementation, contracts, errors, and refactoring. Use when writing or…
git:20261103.998947c · audit A · 51 stars
documentation-criteria SKILL.md skill
shinpr/agentic-code · .agents/skills/documentation-criteria/SKILL.md · Determines which PRD, ADR, Design Doc, and Work Plan a change requires. Use when deciding documentation scope or…
git:20261103.998947c · audit A · 51 stars
implementation-approach SKILL.md skill
shinpr/agentic-code · .agents/skills/implementation-approach/SKILL.md · Selects the smallest sufficient implementation strategy and verification boundary from current requirements and…
git:20261103.998947c · audit A · 51 stars
integration-e2e-testing SKILL.md skill
shinpr/agentic-code · .agents/skills/integration-e2e-testing/SKILL.md · Applies integration and E2E implementation, mock-boundary, and review rules. Use when: writing integration or E2E tests…
git:20261103.998947c · audit A · 51 stars
testing-strategy SKILL.md skill
shinpr/agentic-code · .agents/skills/testing-strategy/SKILL.md · Selects the one owning test for each acceptance criterion at the boundary where its behavior is observable, using…
git:20261103.998947c · audit A · 51 stars
testing SKILL.md skill
shinpr/agentic-code · .agents/skills/testing/SKILL.md · Chooses which tests a change needs, with one owning test per behavioral claim at the boundary where it is observable…
git:20261103.998947c · audit A · 51 stars
AGENTS.md AGENTS.md file
shinpr/agentic-code · AGENTS.md
git:20261103.998947c · audit A · 51 stars

Every file in shinpr/agentic-code

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