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 commands/yu2001-s/opendocu/searchgit clone --depth 1 https://github.com/yu2001-s/OpenDocuWrote 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/commands/yu2001-s/opendocu/search)<a href="https://agentmods.dev/commands/yu2001-s/opendocu/search"><img src="https://agentmods.dev/badge/commands/yu2001-s/opendocu/search.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 | $0.00014 | $0.00194 |
| Opus 5 | $0.00007 | $0.00097 |
| Sonnet 5 | $0.00003 | $0.00039 |
| Haiku 4.5 | $0.00001 | $0.00019 |
Grade A, and why
search 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.
What it actually says
Search OpenDocu for $ARGUMENTS.
Use the deterministic CLI only. Prefer opendocu; if it is unavailable in this plugin session, use node "${CLAUDE_PLUGIN_ROOT}/bin/opendocu.mjs".
Rules:
- Convert
$ARGUMENTSinto anopendocu searchcall with explicit library and keywords. - Do not search with a full natural-language question.
- Pass
--versionwhen the requested or project version is known. - Use
opendocu getfor the best result when full-page context is needed. - Treat semantic cards as optional routing hints; final evidence must come from raw docs.
- Answer from retrieved local docs and mention version/source when version correctness matters.
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.
- 5d ago First seen · 19 lines · 14 tokens per session scan A 281450c6bd5f
search is a command published in the GitHub repository yu2001-s/OpenDocu (2 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 194 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 commands, from other repositories
product-spec
Guide the agent to create or update product-spec docs from a feature brief or code path.
feature-plan
Guide the agent to create or update a feature plan from a short feature request.
scan
Draft a technical spec and roadmap candidates from code, TODOs, and git history.
index
Visual overview of Beacon index — chunks, coverage, provider. Pass --files to list indexed files.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.
estimate
Fast Fermi bracket for a question. Produces an order-of-magnitude bound in under 2 minutes.