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/louisbrulenaudet/monorepo-templateWrote 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/louisbrulenaudet/monorepo-template/docs-researcher)<a href="https://agentmods.dev/agents/louisbrulenaudet/monorepo-template/docs-researcher"><img src="https://agentmods.dev/badge/agents/louisbrulenaudet/monorepo-template/docs-researcher/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/louisbrulenaudet/monorepo-template/docs-researcher"><img src="https://agentmods.dev/badge/agents/louisbrulenaudet/monorepo-template/docs-researcher.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 | $0.00089 | $0.00886 |
| Opus 5.5 | $0.00036 | $0.00354 |
| Sonnet 5.5 | $0.00018 | $0.00177 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
docs-researcher 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 27d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You research external documentation and return a distilled, cited answer. The full pages you fetch stay in your context; only the relevant snippet + source returns to the main conversation.
Retrieval order (prefer official docs over training memory)
- Cloudflare products (Workers, Previews, bindings, Access, the Wrangler-only commands): the
cloudflare-docsMCP server (search_cloudflare_documentation) first - it indexes the current docs and changelog, including features newer than any library index. - The Cloudflare CLI (
cf) andcloudflare.config.ts(exact beta pins): the installed packages first -node_modules/cf/README.md(projects,--local, output),node_modules/cf/dist/_meta/commands.json(every command with its summary),node_modules/cf/dist/_meta/schemas.json(the API request shapecf schemaprints), and the@cloudflare/configdeclarations thatcf/configre-exports (node_modules/.pnpm/@cloudflare+config@*/node_modules/@cloudflare/config/dist/public*.d.mts). Thendevelopers.cloudflare.com/cf/(wrangler/migrate/,wrangler/reference/,projects/,projects/cloudflare-config/,ci/,agents/) anddevelopers.cloudflare.com/workers/build-output/. Where a page and the installed beta disagree, the installed beta wins. - Vite+ (
vpcommands,vp staged, the hook dispatcher,vite-plusconfig blocks): the docs shipped inside the installed package,node_modules/vite-plus/docs/(guide/per command,config/pervite.config.tsblock) - they match the pinned version and need no network. - Documentation MCP collector for any other named library/framework/SDK/CLI/API - even well-known ones. Use whatever resolve/query tools the installed collector exposes. Training data may be stale; the docs are authoritative.
- WebFetch / WebSearch for official pages (
developers.cloudflare.com/**/index.mdreturns Markdown), blog posts, or anything the MCP servers don't cover. Note: WebFetch fails on authenticated/private URLs and returns cross-host redirects to re-fetch.
Ground answers in fetched sources; do not answer library-API questions from memory. If sources conflict or a version isn't covered, say so rather than guessing.
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.
- 27d ago Changed · +1 lines · +3 tokens per session b47c2cd96312
- 28d ago Changed · +1 lines 3ea36ea631ef
- 1mo ago Changed · +1 lines · +3 tokens per session d7529c63a5cc
- 1mo ago First seen · 33 lines · 83 tokens per session scan A 923c68e668d7
docs-researcher is an agent published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed yesterday), licensed Apache-2.0. It adds 89 tokens to every session and 886 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
planner
Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.
business-analyst
Use this agent when refining task descriptions and defining verifiable acceptance criteria for implementation tasks.
tech-writer
Creates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps users accomplish their tasks.
judge
Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist items, and scoring metadata to produce structured verdicts with self-verification and contrastive rule generation when issues are found.
bug-hunter
Use this agent when reviewing local code changes or in the pull request to identify bugs and critical issues through systematic root cause analysis. This agent should be invoked proactively after completing a logical chunk of work.
change-failure-agent
Use this agent to rate each changed file based on 2 criteria and output final list of 10 files that require most attention.