AGENTS.md@plugins/workspace-sandbox/governanceA

This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.

AGENTS.md@plugins/workspace-sandbox/governance from qte77/claude-code-plugins is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add qte77/claude-code-plugins/plugins/workspace-sandbox/governance/AGENTS.md@git:20260404.9bec903

Pins git:20260404.9bec903 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
qte77/claude-code-plugins
Path
plugins/workspace-sandbox/governance/AGENTS.md
Versions recorded
1
Latest version
git:20260404.9bec903, committed Apr 4, 2026
Size
4,282 bytes
Repository stars
3
License
Apache-2.0

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

# Agent Instructions

**Behavioral rules, compliance requirements, and decision frameworks for AI coding
agents.** For technical workflows and coding standards, see
[CONTRIBUTING.md](CONTRIBUTING.md). For project overview, see
[README.md](README.md).

**External References:**

- @CONTRIBUTING.md - Command reference, testing guidelines, code style patterns
- @AGENT_REQUESTS.md - Escalation and human collaboration
- @AGENT_LEARNINGS.md - Pattern discovery and knowledge sharing

## Claude Code Infrastructure

**Rules** (`.claude/rules/`): Session-loaded constraints (always active)
**Skills** (`.claude/skills/`): Modular capabilities with progressive disclosure

## Core Rules & AI Behavior

- Follow SDLC principles: maintainability, modularity, reusability, adaptability
- **Never assume missing context** - Ask questions if uncertain about requirements
- **Never hallucinate libraries** - Only use packages verified in project dependencies
- **Always confirm file paths exist** before referencing in code or tests
- **Never delete existing code** unless explicitly instructed or documented refactoring
- **Document new patterns** in AGENT_LEARNINGS.md (concise, laser-focused, streamlined)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add qte77/claude-code-plugins/plugins/workspace-sandbox/governance/AGENTS.md@sha256:8e4b1495d4df8c18

The line at the top of this page pins the label git:20260404.9bec903, 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_nsyqgopzw3ozjbxy.svg)](https://markdownregistry.com/a/art_nsyqgopzw3ozjbxy)

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

Versions

The registry has recorded 1 version of this file, committed on Apr 4, 2026.

versioncommittedcommitsizeaudit
git:20260404.9bec903 latest2026-04-04 9bec903 4,282 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 (4282 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

qte77/claude-code-plugins · 3 stars · license Apache-2.0 · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nsyqgopzw3ozjbxy
GET https://markdownregistry.com/api/v1/resolve?ref=qte77/claude-code-plugins/plugins/workspace-sandbox/governance/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/8e4b1495d4df8c18e2df9054d471cb1b94bbd6c60c8ea844e9ac6b9a5a47ee79

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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from qte77/claude-code-plugins

committing-staged-with-message SKILL.md skill
qte77/claude-code-plugins · .claude/skills/committing-staged-with-message/SKILL.md · Generate commit message for staged changes, pause for approval, then commit. Stage files first with `git add`, then run…
git:20260224.c52b526 · audit A · 3 stars
AGENTS.md AGENTS.md file
qte77/claude-code-plugins · AGENTS.md
git:20260423.b1a0d81 · audit A · 3 stars
CLAUDE.md CLAUDE.md file
qte77/claude-code-plugins · CLAUDE.md
git:20260619.16d2d56 · audit B · 3 stars
designing-backend SKILL.md skill
qte77/claude-code-plugins · plugins/backend-design/skills/designing-backend/SKILL.md · Designs concise, streamlined backend systems matching exact task requirements. Use when planning APIs, data models…
git:20260929.bb41808 · audit A · 3 stars
compacting-context SKILL.md skill
qte77/claude-code-plugins · plugins/cc-meta/skills/compacting-context/SKILL.md · Compacts verbose context into structured summary. Use after pollution sources (searches, logs, JSON) or at phase…
git:20260322.141a89d · audit A · 3 stars
cross-checking-research SKILL.md skill
qte77/claude-code-plugins · plugins/cc-meta/skills/cross-checking-research/SKILL.md · Cross-check a consumer repo against a research hub both ways — pull hub concepts/sources to cite or adopt, push the…
git:20260925.f555331 · audit A · 3 stars
distilling-plan-learnings SKILL.md skill
qte77/claude-code-plugins · plugins/cc-meta/skills/distilling-plan-learnings/SKILL.md · Extracts decisions, rejected alternatives, and patterns from recent plans into a persistent learnings document. Use…
git:20260929.bb41808 · audit A · 3 stars
handing-off-session SKILL.md skill
qte77/claude-code-plugins · plugins/cc-meta/skills/handing-off-session/SKILL.md · Generate structured session handoff notes for cross-session continuity. Use at end of session or when switching context.
git:20260411.2c6a901 · audit A · 3 stars
mining-session-patterns SKILL.md skill
qte77/claude-code-plugins · plugins/cc-meta/skills/mining-session-patterns/SKILL.md · Extract actionable patterns from Claude Code session JSONL files. Surfaces error→fix sequences, tool failure rates, and…
git:20260929.bb41808 · audit A · 3 stars
orchestrating-parallel-workers SKILL.md skill
qte77/claude-code-plugins · plugins/cc-meta/skills/orchestrating-parallel-workers/SKILL.md · Fan out tasks to parallel background agents with independent context windows. Use when work can be split into…
git:20260929.bb41808 · audit A · 3 stars
persisting-bigpicture-learnings SKILL.md skill
qte77/claude-code-plugins · plugins/cc-meta/skills/persisting-bigpicture-learnings/SKILL.md · Persist bigpicture synthesis as dated snapshots in a learnings hub. Maintains latest pointer + append-only archive for…
git:20260929.bb41808 · audit A · 3 stars
summarizing-session-end SKILL.md skill
qte77/claude-code-plugins · plugins/cc-meta/skills/summarizing-session-end/SKILL.md · Auto-generates a session summary on SessionEnd. Writes structured notes to ~/.claude/session-summaries/ for use by…
git:20260411.af2e024 · audit A · 3 stars

Every file in qte77/claude-code-plugins

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