maintain-agent-instructions SKILL.md skillA
maintain-agent-instructions from arasz/ai-badger is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arasz/ai-badger/maintain-agent-instructions@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arasz/ai-badger
- Path
features/common/skills/maintain-agent-instructions/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Aug 8, 2026
- First version recorded
- Jul 27, 2026
- Size
- 4,459 bytes
- Repository stars
- 3
- License
- MIT
Use when agent instruction files have drifted from each other or from the policy model — CLAUDE.md, copilot-instructions.md, AGENTS.md, hosted-review and path-scoped instruction files — or when validation/drift checks fail in CI. Reconciles them from the machine-readable model in .ai-badger/agent-instructions/.
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
# Maintain agent instructions This skill keeps agent guidance consistent while minimizing always-loaded context. It follows a hub-and-spoke model: one compact, always-loaded entrypoint per agent (`CLAUDE.md`, `.github/copilot-instructions.md`, …) plus detailed, path-scoped or on-demand instruction files. The model is machine-readable so drift between agent files can be checked by script instead of by eye — if the project records this decision as an ADR, link it here. ## When NOT to Use - A single-file typo fix in one instruction file — edit it directly - No drift exists and CI checks pass - Authoring brand-new policy from scratch — that is content work, not reconciliation ## Principles - Use scripts first; inspect only failing files/rules. - Keep each agent's always-loaded entrypoint compact. Put detailed guidance in scoped or on-demand files. - Update the agent-instructions model (`.ai-badger/agent-instructions/model.json` by default; see `references/agent-instruction-model.md`) **when** changing shared policy. - Treat `.github/instructions/*.instructions.md` (or the project's equivalent) as the shared path-scoped implementation rule source. …
Read the whole file at its exact version.
How to install
mdr add arasz/ai-badger/maintain-agent-instructions@sha256:e25fe03f28e10556The line at the top of this page pins the label v1.0.0, 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.
[](https://markdownregistry.com/a/art_bh2mbd73egjnofbr)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 27, 2026 and Aug 8, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-08-08 | 9006bf5 | 4,459 B | A | view · diff |
| v1.0.0 | 2026-08-07 | 4ef57e9 | 4,444 B | A | view · diff |
| v1.0.0 | 2026-08-07 | 013ee4d | 3,896 B | A | view · diff |
| git:20260806.70e384e | 2026-08-06 | 70e384e | 3,541 B | A | view · diff |
| git:20260727.d4facd1 | 2026-07-27 | d4facd1 | 3,561 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4459 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
arasz/ai-badger · 3 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bh2mbd73egjnofbr GET https://markdownregistry.com/api/v1/resolve?ref=arasz/ai-badger/maintain-agent-instructions GET https://markdownregistry.com/api/v1/blob/e25fe03f28e10556704452d30c1b146f78cc100a7b0e8f7cd688c2576a99db69
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.