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 ur-grue/autopunk-media-skills --skill claim-verification-checklistgit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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/ur-grue/autopunk-media-skills/claim-verification-checklist)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/claim-verification-checklist"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/claim-verification-checklist/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/ur-grue/autopunk-media-skills/claim-verification-checklist"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/claim-verification-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01927 |
| Opus 5 | $0.00019 | $0.00963 |
| Sonnet 5 | $0.00008 | $0.00385 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
claim-verification-checklist 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 8d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claim Verification Checklist
What This Skill Does
Generates a point-by-point checklist of every verifiable claim in a draft article, categorized by claim type and accompanied by the specific evidence needed to confirm each one.
When To Use This Skill
- A story is close to publication and needs a systematic fact-check before the editor or legal team sees it
- You are the assigning editor and want to hand a reporter a clear list of what still needs to be verified
- You have inherited a draft from another writer and need to understand what is sourced and what is asserted
- You want to ensure no factual claims slip through on deadline without a documented verification method
What You Need To Provide
Required: The full text of the draft article or a detailed section-by-section summary Optional: A note on which claims are already verified (so the checklist can mark them as such); the publication's fact-checking standard (minimal, standard, or rigorous); the story type (news, investigation, profile, feature)
How the Assistant Approaches This
- Reads the draft and extracts every claim that is factually verifiable — distinguishing factual assertions from opinions, characterizations, and attributed quotes
- Categorizes each claim by type: statistical, biographical, chronological, attribution (quote or paraphrase), official record, scientific, or legal
- For each claim, specifies the minimum evidence standard needed for verification — primary source, secondary corroboration, expert confirmation, or documentary proof
- Flags highest-risk claims: those that are specific, potentially defamatory, or that directly contradict public statements by named individuals
- Closes with a "Next Step" note: which High-risk item to verify first, estimated time to clear the checklist, and whether libel-check-brief should be run alongside for any drafts containing allegations against named individuals
Output Format
Numbered checklist. Each item: Claim (exact quote from draft) | Claim Type | Required Evidence | Risk Level (Low / Medium / High). Grouped by section of the article. Followed by a Summary section noting total claim count, High-risk count, and items already marked as verified. Length scales with article length — typically 400–800 words for a 1,500-word article. Output ends with a "Next Step" note: which High-risk claim to verify first, how long the full check is likely to take, and whether libel-check-brief should be run on the same draft.
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.
- 8d ago First seen · 120 lines · 39 tokens per session scan A fc51e5970bec
claim-verification-checklist is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 39 tokens to every session and 1,927 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
foia-requests
FOIA and public records workflows. Use when drafting requests, tracking submissions, checking exemptions, or appealing denials.
content-access
Legal methods for paywalled and geo-blocked content. Use for paywalls, academic papers, or open access via Unpaywall.
web-archiving
Web archiving and retrieval via Wayback Machine and Archive.today. Use to preserve content, reach dead pages, or save evidence.
brazil-records-requests
Public records requests under Brazil's Access to Information Law (LAI). Use for Fala.BR filings, e-SIC, and CGU/CMRI appeals.
interview-prep
Interview preparation and recording-consent law. Use for research, question frameworks, one-party or all-party consent rules.
Red-Team Verifier
Use when checking whether a legal memo, contract review, demand letter, risk matrix, research summary, draft filing, or other legal AI output is reliable enough to rely on — adversarially stress-testing it before attorney review to surface invented authority, unsupported claims, weak reasoning, jurisdiction and…