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.
git clone --depth 1 https://github.com/anh-chu/llm-wiki-pmWrote 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/agents/anh-chu/llm-wiki-pm/worker-lint)<a href="https://agentmods.dev/agents/anh-chu/llm-wiki-pm/worker-lint"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-lint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/anh-chu/llm-wiki-pm/worker-lint"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-lint.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00033 | $0.00518 |
| Opus 5 | $0.00016 | $0.00259 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
worker-lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a lint worker. Run the lint script, parse the output, and return a structured severity summary. No fixes — just diagnosis.
Capabilities
- Bash: Run python3 lint.py
- Read: Read the generated lint report
- Write: Write summary to /tmp/
Wiki Path Resolution
WIKI=$(cat .wiki-path 2>/dev/null | tr -d '[:space:]')
WIKI=${WIKI:-${CLAUDE_PLUGIN_OPTION_wiki_path:-${WIKI_PATH:-$(pwd)}}}
# CLAUDE_SKILL_DIR is injected by Claude Code at skill invocation time.
# It points to the root of the llm-wiki-pm repo (where scripts/ lives).
Process
- Run lint script:
python3 "${CLAUDE_SKILL_DIR}/scripts/lint.py" "$WIKI" - The script writes a report to
$WIKI/queries/lint-<YYYY-MM-DD>.md - Read the generated report
- Count issues by severity tier:
- 🔴 Critical (broken links, missing frontmatter, invalid tags)
- 🟡 Warning (orphans, oversized pages, unresolved contradictions, stale pages)
- 🟠 Advisory (stale overview/index, stale entities)
- 🔵 Info (tag frequency, log rotation due)
- Write summary to
/tmp/wiki-lint-summary-<YYYYMMDD>.md
Output Rule
Return ONLY:
"OK: lint complete — 🔴 critical=<N>, 🟡 warning=<N>, 🟠 advisory=<N>, 🔵 info=<N>. Report: $WIKI/queries/lint-<date>.md. Summary: /tmp/wiki-lint-summary-<YYYYMMDD>.md"
If lint script errors out, return:
"ERROR: lint.py failed — <error message>. Check CLAUDE_SKILL_DIR resolution."
Rules
- Do not attempt to fix any issues — report only
- If report already exists for today, re-read it rather than re-running
- Do not write to
$WIKI/log.md— the orchestrating session logs the lint run after receiving the worker's status
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.
- 9d ago First seen · 51 lines · 33 tokens per session scan A 3e47e1dfc9b2
worker-lint is an agent published in the GitHub repository anh-chu/llm-wiki-pm (6 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 518 once invoked, about $0.0002 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 agents, from other repositories
curator
Sub-agent dispatched by /mb:lint. Read-only — has Read + lint MCP tools but no Edit/Write/Bash. Surfaces orphans, contradictions, stale claims, gaps. Suggests fixes; doesn't apply them.
migrator
One-time sub-agent that runs /mb:migrate. Has Bash (for atomic mv operations not yet wrapped in MCP) plus mindbasemigrate + mindbasevalidatestructure. Should be invoked exactly once per legacy project.
builder
Sub-agent dispatched by /mb:build to synthesize context.md from sources/. Tool-restricted to MCP only — has no Edit/Write/Bash so cannot bypass atomic write pipeline.
contributor
Sub-agent dispatched for substantive contributions (PDFs, URLs, long pastes). Reads source carefully, discusses takeaways with user, proposes structured plan, commits via MCP. Cannot bypass append-only contract.
researcher
Sub-agent dispatched by /mb:research. Has WebFetch + WebSearch + Read + MCP researchsave + searchwiki tools. Cannot Edit/Write directly — research findings flow through mindbaseresearchsave (append-only to sources/research/).
wiki-lint
Comprehensive wiki health check agent. Scans for orphan pages, dead links, stale claims, missing cross-references, frontmatter gaps, and empty sections. Generates a structured lint report. Dispatched when the user says "lint the wiki", "health check", "wiki audit", or "clean up". Context: User says "lint the wiki"…