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 fmind/dot --skill fact-checkgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/fact-check)<a href="https://agentmods.dev/skills/fmind/dot/fact-check"><img src="https://agentmods.dev/badge/skills/fmind/dot/fact-check/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/fmind/dot/fact-check"><img src="https://agentmods.dev/badge/skills/fmind/dot/fact-check.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 | $0.00019 | $0.00898 |
| Opus 5.5 | $0.00008 | $0.00359 |
| Sonnet 5.5 | $0.00004 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
fact-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 9d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fact-Check
Verify every material claim and link in a draft article, post, talk, or README section, and add primary sources where a claim needs one. Report findings with narrowed wording that would be true today; rewrite only when asked. technical-publishing owns the publication pipeline, and a publishing project's local review skill (for example review-content) takes precedence for its own packages.
Workflow
-
Scope the source: read the whole file and the author's raw notes when they exist; record the revision checked (
git log -1 --format=%h -- <file>plusgit status --short <file>). Published copy is immutable: report findings for an erratum instead of editing it. -
Build the claim ledger: one row per material assertion: versions, defaults, numbers, dates, comparisons, quotations, attributions, availability ("open source", "GA", "free"), and personal results. Skip opinions, but check the facts an opinion rests on.
# Claim (exact quote) Kind Support Verdict Fix -
Verify, do not recognize: confirm each row against a primary source opened in this session: the vendor's documentation or changelog, the repository, the lockfile or installed version, the paper, the official announcement. Prefer the canonical page over an aggregator, blog summary, or model memory. Personal facts trace only to the author's notes or explicit input; never supply them.
-
Check links: run lychee on the file, then open each cited page and confirm it says what the sentence claims; a resolving link that does not support its claim is the worse failure. A bare
--include-fragmentschecks#anchorfragments only; use--include-fragments=fullwhen the draft cites text fragments (#:~:text=).lychee --no-progress --include-fragments --max-retries 2 --format detailed <file> -
Add sources: for an unsupported but true claim, propose the primary link at the claim, not a generic homepage; keep the existing link style (inline, reference, footnote). For an outdated or inflated claim, propose the smaller true form. Never invent a URL; name the missing source instead.
-
Report: verdict counts first (
supported,outdated,unsupported,wrong,broken link), then the ledger rows that need action, ranked by reader impact. Include the date checked: versions, prices, and availability drift.
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.
- 9d ago Changed ad9fb73de7a4
- 11d ago Changed 34d7393b926e
- 12d ago First seen · 46 lines · 19 tokens per session scan A a73dafbd301b
fact-check is a skill published in the GitHub repository fmind/dot (11 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 898 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-05.
Other skills, from other repositories
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.