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 skills add lttr/claude-marketplace --skill docs-checkergit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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/skills/lttr/claude-marketplace/docs-checker)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/docs-checker"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/docs-checker/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/skills/lttr/claude-marketplace/docs-checker"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/docs-checker.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 | $0.00064 | $0.00859 |
| Opus 5 | $0.00032 | $0.00430 |
| Sonnet 5 | $0.00013 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade C, and why
docs-checker scanned grade C with 1 finding 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 10d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
- `<!-- docs-check-ignore -->` at the end of a line How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Checker
Audit the repository's context files — CLAUDE.md at any depth, the .claude/ tree (skills, rules, commands), READMEs, and the docs tree — for correctness. This is a conservative audit: report findings with evidence, do not rewrite anything unless the user asks. Style, tone, and level of detail are the author's choices and are out of scope.
Prerequisites
- Node.js >= 22 (the bundled script uses
fs.globSync)
Workflow
1. Deterministic pass
Run the bundled checker from the repo root:
node ${CLAUDE_SKILL_DIR}/scripts/docs-check.mjs $ARGUMENTS
It needs no config and no dependencies. What it does:
- Checks relative/absolute markdown links and image assets against the working tree
- Checks backticked source paths in prose (
src/foo.ts,@alias/bar) against the codebase, resolving tsconfig/package.json aliases - Scans the paths you name (or the repo's docs tree by default), plus every
CLAUDE.mdand the whole.claude/tree automatically - Cross-repo docs: pass
--repo=NAME:DIRfor each sibling checkout the docs reference
Exit 0 is clean, 1 means findings (printed as line:col rule message with did-you-mean hints), 2 is bad invocation. Its findings are ground truth — do not second-guess them.
2. Semantic pass
Read the context files the script scanned — but keep this pass on a scoped diet: CLAUDE.md files, the .claude/ tree, and top-level READMEs. Do not crawl the whole docs tree unless the user asked; the script already covered the wide surface.
Look only for claims you can verify against the repo right now:
- Commands or scripts quoted in docs that don't exist (check
package.jsonscripts,Makefile, bundled scripts) - Described behavior that contradicts the code it points at (read the code before claiming this)
- Instructions that contradict each other across context files
- Sections duplicated between files (e.g. README and CLAUDE.md drifting apart)
- References to tools, versions, or structures the repo no longer uses
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 70 lines · 64 tokens per session scan C e65636c262f2
docs-checker is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 859 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
hook-factory
Generate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.