CLAUDE.md@.ai-badgerA

CLAUDE.md@.ai-badger from arasz/ai-badger is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.

Install it, pinned
mdr add arasz/ai-badger/.ai-badger/CLAUDE.md@git:20261007.5d99092

Pins git:20261007.5d99092 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
CLAUDE.md file
Repository
arasz/ai-badger
Path
.ai-badger/CLAUDE.md
Versions recorded
5
Latest version
git:20261007.5d99092, committed Oct 7, 2026
First version recorded
Oct 3, 2026
Size
17,272 bytes
Repository stars
3
License
MIT

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

# ai-badger

Agent-instruction framework distributed as a Claude Code plugin. Python 3.10+ scripts (detect/scaffold/validate/index_build/drift) materialize a per-repo .ai-badger/ scaffold from a features/{stack|common}/{feature} catalog. engine/requirements.txt declares three runtime dependencies plus one optional wrapper guard: jsonschema (required; validation refuses rather than silently passing), pyyaml (optional, guarded, and degrades to a printed note), and pydantic (required; the task-plan model and its schema generator); semantica is needed only by the optional wrapper. The task-graph plan server/CLI are PEP 723 scripts launched via `uv run --script`, so the consumer-side prerequisite is uv (it fetches pydantic>=2.12,<3 into its cache on first launch, with no pip install and no project-venv pollution). The plan DAG layer is stdlib graphlib; networkx is deliberately not used. Two .mjs helper scripts under skills/maintain-agent-instructions/.

> Domain: Developer tooling: agent instruction catalogs and repo scaffolding.
> Stacks: python, js, github, claude, hermes, pi, ts, node, changelog
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add arasz/ai-badger/.ai-badger/CLAUDE.md@sha256:20bea8c417037e12

The line at the top of this page pins the label git:20261007.5d99092, 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_3rzfbcdj4qkmza34.svg)](https://markdownregistry.com/a/art_3rzfbcdj4qkmza34)

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

Versions

The registry has recorded 5 versions of this file, between Oct 3, 2026 and Oct 7, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261007.5d99092 latest2026-10-07 5d99092 17,272 BA view · diff
git:20261004.c5f29dd2026-10-04 c5f29dd 17,272 BA view · diff
git:20261003.a97f0cd2026-10-03 a97f0cd 17,272 BA view · diff
git:20261003.338b7a42026-10-03 338b7a4 17,275 BA view · diff
git:20261003.94d6d4f2026-10-03 94d6d4f 17,275 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (17272 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

arasz/ai-badger · 3 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3rzfbcdj4qkmza34
GET https://markdownregistry.com/api/v1/resolve?ref=arasz/ai-badger/.ai-badger/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/20bea8c417037e124742887dac3f7f47daf8594a72a1fb02e3befd1d6b4065d6

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: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.

More from arasz/ai-badger

ai-raccoon-memory SKILL.md skill
arasz/ai-badger · .ai-badger/skills/ai-raccoon-memory/SKILL.md · Use when a project needs a memory server — search project and shared memory first, write durable facts with source…
v0.2.0 · audit A · 3 stars
archify SKILL.md skill
arasz/ai-badger · .ai-badger/skills/archify/SKILL.md · Use when the user asks to visualize system architecture, infrastructure, cloud/security topology, technical workflows…
v2.16.0 · audit A · 3 stars
artifact-verification SKILL.md skill
arasz/ai-badger · .ai-badger/skills/artifact-verification/SKILL.md · Use when verifying changed artifacts that lack a canonical test gate — specs, docs, manifests, generated files…
v1.0.0 · audit A · 3 stars
auto-wm SKILL.md skill
arasz/ai-badger · .ai-badger/skills/auto-wm/SKILL.md · Use when the user wants Claude to auto-approve tool calls — "enable autonomic/autonomous work mode", "/auto-wm"…
v1.0.0 · audit A · 3 stars
browser-usage SKILL.md skill
arasz/ai-badger · .ai-badger/skills/browser-usage/SKILL.md · Use when interacting with web pages, running manual E2E browser tests, testing UI flows, or inspecting live web…
v1.0.0 · audit A · 3 stars
call-behaviorist SKILL.md skill
arasz/ai-badger · .ai-badger/skills/call-behaviorist/SKILL.md · Use when ai-badger's own machinery needs to be observed — "did that hook even run?", "enable debug logging", "why is…
v1.0.0 · audit A · 3 stars
code-review-checklist SKILL.md skill
arasz/ai-badger · .ai-badger/skills/code-review-checklist/SKILL.md · Use when reviewing code — a PR, a diff, or freshly written changes — and you want concrete pass/fail checks rather than…
v1.0.0 · audit B · 3 stars
code-review-evidence SKILL.md skill
arasz/ai-badger · .ai-badger/skills/code-review-evidence/SKILL.md · Use when reviewing code that wraps external libs/extensions/SDKs/CLIs, or QA-reviewing a test harness: verify…
v1.0.0 · audit A · 3 stars
code-review SKILL.md skill
arasz/ai-badger · .ai-badger/skills/code-review/SKILL.md · Use when performing a code review in this repository — reviewing a pull request, a branch diff, or a requested…
v1.0.0 · audit A · 3 stars
commit-reminder SKILL.md skill
arasz/ai-badger · .ai-badger/skills/commit-reminder/SKILL.md · Use when a project has accumulated uncommitted changes and nobody has said so out loud — several edits in a row with no…
v1.0.0 · audit A · 3 stars
complete-project-scope-code-review SKILL.md skill
arasz/ai-badger · .ai-badger/skills/complete-project-scope-code-review/SKILL.md · Use when the whole project — not a diff — is the review target and the result must survive being acted on: "review the…
v1.0.0 · audit A · 3 stars
create-task-spec SKILL.md skill
arasz/ai-badger · .ai-badger/skills/create-task-spec/SKILL.md · Use when a feature idea needs to become an exact, agreed specification before anyone builds it — "spec this out"…
v1.0.0 · audit A · 3 stars

Every file in arasz/ai-badger

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