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 kyungseo/skillstead --skill docs-claim-checkgit clone --depth 1 https://github.com/kyungseo/skillsteadWrote 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/kyungseo/skillstead/docs-claim-check)<a href="https://agentmods.dev/skills/kyungseo/skillstead/docs-claim-check"><img src="https://agentmods.dev/badge/skills/kyungseo/skillstead/docs-claim-check.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 36 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00180 | $0.02768 |
| Opus 5 | $0.00090 | $0.01384 |
| Sonnet 5 | $0.00036 | $0.00554 |
| Haiku 4.5 | $0.00018 | $0.00277 |
Grade A, and why
docs-claim-check 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 today.
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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-claim-check
Compare what public-facing documentation claims with what the provided evidence shows, one atomic claim at a time. Output findings with confidence labels and an explicit statement of what was (and was not) reviewed.
This skill renders a judgment backed by evidence. It is not a checklist, not a linter, and not a substitute for code review.
Before any tool use
First confirm that the target documentation or claim text is supplied in the conversation. If it is absent, ask the user to provide it. Do not list, search, or read repository files and do not execute a command to locate the target or evidence.
If the target is present but evidence is incomplete, continue with the existing evidence-request procedure below. Ask only for the missing evidence; do not ask the user to provide the target again.
Boundaries (read first)
These are contractual guardrails. They are enforced by this skill's procedure and verified through its output format — a markdown skill cannot technically prevent a host from running commands, so compliance must be visible in the output itself.
- Public-facing documentation claims only. README files, release notes, install and usage docs, landing-page copy. Decline internal design docs and requests to judge code quality — point to a code-review tool instead.
- Never execute commands. If a claim needs a command output that was not provided, do not run it — emit an evidence request naming the exact command or file that would settle the claim.
- Never generate fixes. No patches, no replacement wording, no rewritten docs. Findings and caveats only. If asked for a fix, decline and restate this boundary.
- Privacy. Process everything locally in the conversation. Do not accept secrets, credentials, or customer data as evidence — ask for a redacted or minimized excerpt instead.
Every output must end with the Boundary Notes block (see Output Contract) so that compliance is auditable.
What ships with it
4 files 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.
- today Changed 3630b0833d64
- 8d ago First seen · 243 lines · 180 tokens per session scan A 278a6ec3def3
docs-claim-check is a skill published in the GitHub repository kyungseo/skillstead (78 stars, last pushed yesterday), licensed Apache-2.0. It adds 180 tokens to every session and 2,768 once invoked, about $0.0009 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 skills, from other repositories
fireworks-tech-graph
Create technical diagrams such as software architecture, data flow, flowcharts, sequence diagrams, C4 reviews, cloud deployments, event streams, observability investigations, agent/memory systems, UML, ER, network topology, timelines, and technical concept maps, then export SVG, PNG, focused semantic SVG-to-GIF…
data-viz-renderer
Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards. Offers 8 color palettes and built-in icons with no external dependencies. Triggered when users request data visualization, infographics, charts, or dashboards.
reimagine-it
Content-Derived Design — reads existing HTML and writes a stronger standalone page from headings, facts, names, dates, numbers, links, emails, and colors already in that file. CLI: npx reimagine-it --auto -i page.html -o out.html; also variations, lock, and audit. Use when the user says /reimagine-it, "reimagine it"…
lov-gh-access
Open a private GitHub repo to external clients or contractors without making it public. Accepts a mixed list of GitHub usernames and/or email addresses, resolves each to a GitHub account (falling back to an email invitation when the user has no discoverable account yet), and invites them as collaborators with a chosen…
lov-gh-tidy
Interactive GitHub repo hygiene skill. Lists all open issues, PRs, stale branches, and orphan labels, shows a summary of each with analysis, then asks the user how to handle each item (close, merge, comment, delete, keep). Executes all chosen actions via gh CLI. Use when the user says "清理 GitHub", "tidy repo", "clean…
hyperweave-verbs
Read, verify, mutate, and round-trip HyperWeave living artifacts via the verb algebra instead of vision-parsing the SVG.