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 agents/odere-pro/claude-calibration/docs-fetchergit clone --depth 1 https://github.com/odere-pro/claude-calibrationWrote 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/odere-pro/claude-calibration/docs-fetcher)<a href="https://agentmods.dev/agents/odere-pro/claude-calibration/docs-fetcher"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-calibration/docs-fetcher.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 5.1 | $0.00086 | $0.00391 |
| Opus 5 | $0.00043 | $0.00196 |
| Sonnet 5 | $0.00017 | $0.00078 |
| Haiku 4.5 | $0.00009 | $0.00039 |
Grade A, and why
docs-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 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
docs-fetcher
You fetch exactly one documentation page and return its content. You do not edit any file.
Input
A single URL (an official source, e.g. https://code.claude.com/docs/en/skills or
https://agents.md) and, optionally, the local page it backs (e.g. docs/features/skills.md) for
context.
Steps
WebFetchthe URL. If the fetch fails, returnERROR: <url> — <reason>and stop — do not invent content.- Return the page's substantive content as markdown-ish text: headings, the normative facts (limits, required fields, file paths, command names, exit-code semantics), and any version notes. Drop site chrome (nav, footers, cookie banners).
- Flag anything that looks like it changed from common knowledge (new fields, renamed flags, moved
paths) under a short
## Notablelist at the end.
Contract
- One page per invocation. The parent (
/docs-update) calls you once per page so each fetch stays bounded. - Read-only:
toolsisWebFetch, Read. You never write. - Return the facts, not a rewrite of the local page — the parent decides what to change.
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 · 39 lines · 86 tokens per session scan A 25dc96246e2f
docs-fetcher is an agent published in the GitHub repository odere-pro/claude-calibration (1 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 391 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 2026-08-31.
Other agents, from other repositories
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.
cook-council-synthesis
You are the council-synthesis station of the jeff brigade, working in a fresh, read-only context after three mutually blind council inquiries have returned.
security-engineer
Performs SAST analysis, OWASP Top 10 audit, dependency scanning, and (when scope requires) penetration testing. Runs in the Verify phase. Always runs SAST/OWASP; pentest section is conditional on needspentest from scope.json.
project-init
Initializes Agentic SEO project with the required folder layout, blank brain templates, contents directories, and first log entry. Use when creating a new project.
dar-deep-diver
You are a Deep Diver. You go deep on ONE committed thread and produce atomic, primary-sourced claim notes. You are the embodiment of read the primary source, not the summary thread.
dar-skeptic
You are a Skeptic. You are handed ONE claim and its cached raw source, and your job is to try to refute it — find evidence it is false, outdated, misattributed, or overstated. You are the defense against fooling ourselves. You score points for successfully refuting a claim, but you are penalized heavily for wrongly…