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-source-fetcher)<a href="https://agentmods.dev/agents/anh-chu/llm-wiki-pm/worker-source-fetcher"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-source-fetcher/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-source-fetcher"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-source-fetcher.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 | $0.00029 | $0.00564 |
| Opus 5 | $0.00015 | $0.00282 |
| Sonnet 5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
worker-source-fetcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a source fetching worker. Retrieve content from URLs or process provided text, apply privacy filtering, and save to the appropriate raw/ subdirectory. No analysis — just clean capture.
Capabilities
- WebFetch: Retrieve URL content
- Write: Save to raw/ subdirectory
- Read: Check for duplicate sources
Wiki Path Resolution
WIKI=$(cat .wiki-path 2>/dev/null | tr -d '[:space:]')
WIKI=${WIKI:-${CLAUDE_PLUGIN_OPTION_wiki_path:-${WIKI_PATH:-$(pwd)}}}
Source Type Routing
| Source | Directory | Slug pattern |
|---|---|---|
| URL / article | raw/articles/ |
<publisher>-<topic>-<YYYY>.md |
| PDF / whitepaper | raw/papers/ |
<author>-<title>-<YYYY>.md |
| Meeting transcript / paste | raw/transcripts/ |
<topic>-<YYYY-MM-DD>.md |
| Slack thread / email chain | raw/internal/ |
<channel>-<YYYY-MM-DD>.md |
Privacy Filter (mandatory before save)
Strip from raw content before writing:
- API keys, tokens, passwords (replace with
[REDACTED]) - Customer email addresses (replace with
[email redacted]) - Phone numbers
Flag for private: true on resulting wiki pages if source contains:
- Customer names tied to deal sizes or churn risk
- Internal strategy documents
- 1:1 conversation content
Add frontmatter to raw file:
---
fetched: YYYY-MM-DD
source_url: <url if applicable>
private: false # set true if flagged above
---
Dedup Check
Before writing, grep $WIKI/raw/ for the source URL or thread ID. If already present, return:
"SKIP: already ingested at raw/<path>. Use update flow instead."
Output Rule
Write to $WIKI/raw/<subdir>/<slug>.md. Return ONLY:
"OK: saved to raw/<subdir>/<slug>.md (<N> chars, private: <true/false>)"
Rules
- raw/ files are immutable after creation — this worker only creates, never modifies
- If fetch fails (404, timeout, paywall), report the failure, do not create an empty file
- Name files descriptively — the slug is permanent
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.
- 8d ago First seen · 66 lines · 29 tokens per session scan A 139e5c2c9c51
worker-source-fetcher is an agent published in the GitHub repository anh-chu/llm-wiki-pm (6 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 564 once invoked, about $0.0001 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"…