Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/qte77/claude-code-plugins/maintaining-agents-mdnpx skills add qte77/claude-code-plugins --skill maintaining-agents-mdgit clone --depth 1 https://github.com/qte77/claude-code-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/qte77/claude-code-plugins/maintaining-agents-md)<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/maintaining-agents-md"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/maintaining-agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00053 | $0.00834 |
| Opus 5 | $0.00026 | $0.00417 |
| Sonnet 5 | $0.00011 | $0.00167 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
maintaining-agents-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Agent Governance Files
Scope: $ARGUMENTS
Keeps agent governance files synchronized with codebase state. Detects stale references, missing updates, and promotion candidates.
Governance Files
| File | Authority | Purpose |
|---|---|---|
AGENTS.md |
Behavioral | Rules, role boundaries, compliance requirements |
CONTRIBUTING.md |
Technical | Workflows, commands, coding standards |
AGENT_LEARNINGS.md |
Knowledge | Accumulated patterns and solutions |
AGENT_REQUESTS.md |
Escalation | Active blockers requiring human input |
When to Use
- After PRs that change project structure, commands, or patterns
- At sprint start/end for governance health check
- When promoting patterns from
AGENT_LEARNINGS.mdto.claude/rules/ - After
make validatepipeline or Makefile changes - When adding/removing skills or plugins
Modes
audit (default)
Scan governance files for staleness and inconsistencies.
Checks:
- Stale paths: Grep governance files for
src/,docs/,tests/paths. Verify each path still exists. - Stale commands: Parse
CONTRIBUTING.mdcommand reference table. Verify eachmakerecipe exists inMakefile. - Missing learnings: Check recent git log for patterns not yet in
AGENT_LEARNINGS.md. Ifralph/docs/LEARNINGS.mdexists, check it too. - Resolved requests: Check
AGENT_REQUESTS.mdentries — flag any whose referenced files/issues no longer exist. - Role boundary drift: Verify AGENTS.md role definitions match current
.claude/skills/inventory.
Output: Findings table with file, line, issue type, description.
sync
Fix staleness found by audit. For each finding:
- Propose the specific edit
- Apply on user approval
- Follow priority order: AGENTS.md > CONTRIBUTING.md > AGENT_LEARNINGS.md > AGENT_REQUESTS.md
promote
Evaluate AGENT_LEARNINGS.md entries for promotion per the criteria in
.claude/rules/compound-learning.md (3rd occurrence → rule, recurring → skill).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 95 lines · 53 tokens per session scan A cf451a59f632
maintaining-agents-md is a skill published in the GitHub repository qte77/claude-code-plugins (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 53 tokens to every session and 834 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orchestrator
FULLY AUTONOMOUS Flutter development pipeline orchestrator. Smart routing: PM analyzes -> creates targeted tasks -> Orchestrator executes only needed agents. Supports Asana task URLs. Includes QE verification via Maestro E2E tests. 7-phase flow: PM -> TodoWrite -> Execute -> Review -> Tests -> QE E2E -> Close.
flutter-guide
Flutter/BLoC Clean Architecture patterns, review checklists, and testing guides. Background knowledge for flutter-dev, flutter-reviewer, flutter-tester. Not user-invocable.
maestro-flutter
Maestro E2E testing knowledge for Flutter apps. YAML-based flows, TestKeys, visual regression, Maestro MCP integration. Background knowledge for QE E2E testing phase.
android-kotlin-compose
Android development with Kotlin and Jetpack Compose. Use when user mentions "Compose", "Jetpack Compose", "Material3", "Hilt", "Room", "ViewModel", or needs to build Android UI, implement MVVM architecture, manage Compose state, or integrate Jetpack libraries (Navigation, Room, Hilt, ViewModel). Triggers on…
android-kotlin-coroutines
Android development with Kotlin Coroutines and Flow. Use when user mentions "coroutines", "suspend", "Flow", "StateFlow", "SharedFlow", "viewModelScope", "lifecycleScope", or needs to implement async programming, handle structured concurrency, integrate coroutines with Retrofit/Room/WorkManager, or write coroutine…
codex-advisor
Advisory consultation skill for architectural reviews, design decisions, code analysis, and technology evaluation. Codex provides recommendations without making code changes. Invoked by phrases like "consult Codex", "get Codex's opinion", "ask Codex about", "have Codex review", "Codex analysis", "validate this…