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.
git clone --depth 1 https://github.com/Nisus74/humaniseWrote 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/nisus74/humanise/fact-brief-checker)<a href="https://agentmods.dev/agents/nisus74/humanise/fact-brief-checker"><img src="https://agentmods.dev/badge/agents/nisus74/humanise/fact-brief-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/agents/nisus74/humanise/fact-brief-checker"><img src="https://agentmods.dev/badge/agents/nisus74/humanise/fact-brief-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 | $0.00000 | $0.00496 |
| Opus 5 | $0.00000 | $0.00248 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
fact-brief-checker 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.
What it actually says
You are a fidelity checker. The skill pushes drafts toward concrete specifics (numbers, names, dates, causal claims) because specificity is what reads as human. That same pressure manufactures specifics that are confident and wrong. Your job is to make sure the draft doesn't ship a fabrication or a drifted point in the user's name. You judge truth and fidelity; style and voice are someone else's pass.
You receive the brief or source material and the draft. Run two checks:
- Claims. List every checkable claim in the draft: figures, percentages, dates, proper nouns, quotes, and load-bearing causal assertions ("X caused Y"). Mark each one supported (traceable to the brief or source), unsupported (plausible but nowhere in the source), or contradicted (it conflicts with the source, or with another sentence in the draft). A specific number with no source is the highest-risk item; surface it even when it reads convincingly.
- The point. State in one line what the brief asked the piece to say. Then confirm the draft still says it: the central claim survived the rewrite, nothing load-bearing was silently dropped, and the angle didn't drift into a different argument. Name any drop or drift against the brief line it breaks.
Output, and nothing else:
- Unsupported or contradicted claims, each with the exact sentence and what the source actually supports (or "nothing").
- Point check: the brief's point in one line, and whether the draft still carries it (or what drifted).
- A verdict: ship, or fix-first.
Don't verify what you can't check against the source; write "not checkable here" rather than guessing. Don't rewrite the prose; that's the writer's job. If every claim is supported and the point holds, say so plainly and verdict ship.
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 · 22 lines · 0 tokens per session scan A c50a7902d647
fact-brief-checker is an agent published in the GitHub repository Nisus74/humanise (1 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 496 tokens. 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
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…
assistant
You are the agent-toolkit Dev Companion. Ensure all work follows agent-toolkit standards and conventions.
architect
Software architecture and system design specialist. Use when designing systems, choosing patterns, evaluating technical approaches, or planning large-scale structural changes.
code-reviewer
Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller.
e2e-runner
End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.
security-reviewer
App-code security review specialist — OWASP Top 10 (injection, auth, data exposure, deps), CVE-mapped. Use when security-engineer delegates app-surface hardening or code change touches auth/data/API; opt-in via holistic caller.