agentmods.dev

maintainer

maintainer is a command for Claude Code from Pratiyush/llm-wiki. It costs 0 tokens per session (942 once invoked), scanned A, original, MIT.

A maintainer command that loads the llmwiki repository's governance and maintenance rules into the session. Governance documents define how contributions, reviews, releases, security, and issue handling should work.

In plain words
What is it for?
It prepares a session for reviewing pull requests, triaging issues, and following the repository's maintenance process.
Why use it?
It gives later maintenance actions the shared project rules and context they need.

Command for Claude Code

Part of the llm-wiki plugin — 6 skills, 18 commands shipped together

not rated 383 +3 2mo ago A scan 0 tokens original MIT
View the source file Pratiyush/llm-wiki
Install

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.

agentmods
npx agentmods add commands/pratiyush/llm-wiki/maintainer
Clone the repo
git clone --depth 1 https://github.com/Pratiyush/llm-wiki

Made for: Claude Code.

Or install llm-wiki, the plugin that ships this one along with the rest of its 6 skills, 18 commands.

Wrote 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.

agentmods badge for maintainer

README.md
[![agentmods](https://agentmods.dev/badge/commands/pratiyush/llm-wiki/maintainer.svg)](https://agentmods.dev/commands/pratiyush/llm-wiki/maintainer)
Your own site
<a href="https://agentmods.dev/commands/pratiyush/llm-wiki/maintainer"><img src="https://agentmods.dev/badge/commands/pratiyush/llm-wiki/maintainer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00942
Opus 5 $0.00000 $0.00471
Sonnet 5 $0.00000 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 5d ago against content hash 0d0b971a5bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maintainer 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 5d 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.

.claude/commands/maintainer.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-skill that loads all llmwiki governance docs and exposes the three maintainer slash commands.

Usage: /maintainer

Run this once at the start of a maintainer session. It loads every doc in docs/maintainers/ plus the top-level governance files (CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md) as context, so every subsequent action in the session has the full bar in mind.

Workflow

  1. Load the governance scaffold — read all of these, in order:

    • CONTRIBUTING.md (short rules for contributors)
    • SECURITY.md (privacy + disclosure process)
    • CODE_OF_CONDUCT.md (behavioral standards)
    • docs/maintainers/README.md (index of maintainer docs)
    • docs/maintainers/ARCHITECTURE.md (layer boundaries + what NOT to add)
    • docs/maintainers/REVIEW_CHECKLIST.md (canonical review bar)
    • docs/maintainers/RELEASE_PROCESS.md (version bump flow)
    • docs/maintainers/TRIAGE.md (label taxonomy + stale policy)
    • docs/maintainers/ROADMAP.md (near-term plan)
    • docs/maintainers/DECLINED.md (prior rejections)

  2. Check current state — run these in parallel so you know what the queue looks like:

    gh pr list --state open --limit 20
gh issue list --state open --limit 50
gh run list --branch master --limit 5

  3. Report a status summary — for the user:

    • Number of open PRs + their authors + ages
    • Number of untriaged issues (no enhancement/bug/chore label)
    • Number of open priority:must items
    • Master CI status (last 3 runs)
    • Any red CI runs that need attention
    • Any PR stuck > 7 days (escalation triggers per TRIAGE.md)

  4. Offer the three sub-commands — remind the user that they can:

    • Run /review-pr <N> to review a specific PR against the canonical checklist
    • Run /triage-issue <N> to apply the label taxonomy to an untriaged issue
    • Run /release <version> to walk the release process for a new version bump

  5. Recommend the next action — based on the status:

    • If there's a stuck PR, recommend /review-pr
    • If there's an untriaged issue, recommend /triage-issue
    • If the CHANGELOG has a coherent batch of ## [Unreleased] entries and no blockers, recommend /release
    • If none of the above, say "queue is clean" and stop.

Read the full file on GitHub · 89 lines

Changes

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.

  1. 5d ago First seen · 89 lines · 0 tokens per session scan A 0d0b971a5bad

Subscribe to this mod's changes

maintainer is a command published in the GitHub repository Pratiyush/llm-wiki (383 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 942 tokens. 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 2026-08-30.

aiclaude-codecodex-clicursordeveloper-toolskarpathy
Related

Other commands, from other repositories

scan-project

Scan a project and suggest domain-expert skills it would benefit from, then draft the ones the user picks.

wonsukchoi/domain-experts · 22 tokens

sync-doctor

Detect MCP config drift and parse errors between Claude Code and target AI agents.

Leoyang183/sync-agents-settings · 18 tokens

sync-instructions

Sync CLAUDE.md instruction files to other AI agents (Gemini, Codex, OpenCode, Kiro, Cursor, Kimi, Vibe, Qwen, Amp).

Leoyang183/sync-agents-settings · 41 tokens

sync-validate

Validate Claude MCP schema and target capability compatibility before syncing.

Leoyang183/sync-agents-settings · 14 tokens

sync-list

List all MCP servers configured in Claude Code with transport type and source.

Leoyang183/sync-agents-settings · 16 tokens

/opsx-propose

Propose a new change - create it and generate all artifacts in one step.

amittamari/hop · 21 tokens