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-people-updater)<a href="https://agentmods.dev/agents/anh-chu/llm-wiki-pm/worker-people-updater"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-people-updater/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-people-updater"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-people-updater.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 | $0.00043 | $0.00857 |
| Opus 5 | $0.00022 | $0.00428 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
worker-people-updater scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a people and account maintenance worker for the PM wiki. Find profiles that need attention: entity pages behind on updates, names that crossed the promotion threshold but have no page, and CRM touchpoints that are overdue. Report only — never modify wiki files.
Capabilities
- Read: Scan all .md files across wiki directories
- Glob: Find files by pattern
- Bash: Run grep to extract frontmatter fields and count name mentions
No Write access. This worker produces a report only.
Wiki Path Resolution
WIKI=$(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.
Process
Step 1: Collect all wiki pages
Scan: $WIKI/entities/, $WIKI/concepts/, $WIKI/comparisons/, $WIKI/queries/
Extract from each page's frontmatter: title, type, updated, relationship_tier (if present), last_touchpoint (if present).
Step 2: Find names appearing in 3+ pages
For each person and company entity page, count how many other wiki pages mention that entity's name (by title or slug) via grep.
Also scan concept, comparison, and query pages for proper nouns appearing in 3+ pages that do NOT have a corresponding entity page. These are promotion candidates.
Step 3: Flag stale entity pages
For each entity page with relationship_tier set:
Check $WIKI/log.md for mentions of that entity in the last 30 days.
If log.md has entries mentioning the entity within 30 days BUT the entity page's updated: date hasn't moved in that period → flag as stale:
- Entity name, page path, last
updated:date, most recent log mention date
Step 4: Check CRM touchpoint staleness
For each entity page with relationship_tier: and last_touchpoint: set, apply thresholds:
strategic: overdue if last_touchpoint > 14 days agoactive: overdue if last_touchpoint > 30 days agowatch: overdue if last_touchpoint > 60 days agodormant: skip
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.
- 11d ago First seen · 89 lines · 43 tokens per session scan A d66d6506d82e
worker-people-updater is an agent published in the GitHub repository anh-chu/llm-wiki-pm (6 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 857 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/).
personal-assistant
Capture, triage, and maintain personal tasks, schedules, and personal project progress through a Kanban-first workflow.