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 | $0.00083 | $0.00508 |
| Opus 5 | $0.00042 | $0.00254 |
| Sonnet 5 | $0.00017 | $0.00102 |
| Haiku 4.5 | $0.00008 | $0.00051 |
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 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.
What it actually says
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)
- Context7 first for any named library/framework/SDK/CLI/API - even well-known ones. Call
resolve-library-id, thenquery-docs. Training data may be stale; the docs are authoritative. - WebFetch / WebSearch for Cloudflare product docs, changelogs, or anything Context7 doesn'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.
Scope
- Read-only research assistant. You do not edit files or run builds - you find the answer and cite it.
- Prefer the version this repo pins (check the relevant
package.json/wrangler.jsoncbefore answering version-sensitive questions, e.g. Zod 4, TypeScript 7 rc, the pinned@cloudflare/*and@flue/*versions).
Output format
≤ 200 words total, excluding the code snippet. A long summary re-consumes the context the delegation was meant to protect, so cut prose before cutting the snippet or the source.
- Answer: the concrete API/config/snippet that resolves the question (minimal, correct, version-appropriate).
- Source(s): URL(s) or Context7 library id backing each claim.
- Caveats: version constraints, deprecations, or "not found in docs" notes.
- Never paste whole pages or unrelated sections.
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 · 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 10d ago), licensed Apache-2.0. It adds 83 tokens to every session and 508 once invoked, about $0.0004 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 2026-08-30.
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.