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 isvlasov/rageatc-oss --skill verifying-claimsgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/verifying-claims)<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/verifying-claims"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/verifying-claims/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/isvlasov/rageatc-oss/verifying-claims"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/verifying-claims.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 | $0.00043 | $0.02093 |
| Opus 5 | $0.00022 | $0.01046 |
| Sonnet 5 | $0.00009 | $0.00419 |
| Haiku 4.5 | $0.00004 | $0.00209 |
Grade A, and why
verifying-claims 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 12d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying Claims
Medium freedom: follow the phases sequentially (extract → mode → assess sources → weight → triangulate → resolve conflicts → calibrate), adapting verification depth to claim significance and risk.
Non-negotiable standards:
- Identical verification standards for all claims (non-partisanship)
- Document every source consulted — transparent audit trail
- Calibrated confidence language; never present uncertain claims as certain
- Surface disagreements between authoritative sources rather than hiding them
- Primary sources over secondary, secondary over tertiary
Phase 1 — Extract and categorise claims
Extract discrete, verifiable assertions: statements presented as fact; names, dates, numbers, statistics, events; asserted causal relationships and predictions; factual claims embedded in interpretive passages.
Example: "The UK's ageing population, which reached 67.3 million in 2021, will strain healthcare resources" yields three claims — population 67.3 million in 2021 (factual), population ageing (factual, needs definition), will strain healthcare (interpretive/predictive).
Categorise each claim:
- Factual/verifiable — provable with objective evidence (statistics, dates, events, findings) → full verification
- Interpretive/analytical — facts plus judgement (causal claims, predictions, impact assessments) → verify the factual basis, assess the reasoning
- Opinion — values, beliefs, preferences, aesthetics → do not fact-check; flag as opinion
Filter uncheckable claims and note why: future predictions, personal experiences, vague claims ("many people believe…"), hypotheticals.
Prioritise by significance (affects key conclusions or decisions), specificity, risk, and feasibility.
Phase 2 — Select verification mode
Mode A — Retrospective (sources provided). Check claims against provided documents; the standard mode for detecting extrinsic hallucinations in AI-generated content. Compare each claim systematically against the sources and flag:
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.
- 12d ago First seen · 145 lines · 43 tokens per session scan A ce9b7c29e356
verifying-claims is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 2,093 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 2026-08-31.
Other skills, from other repositories
design-method
Use when starting any design task — resolves register, sets the 3 dials, locks Gate 0, and routes to the right move and target skill.
design-webapp
Use when building or extending a dashboard, SaaS screen, or any authenticated app surface — use design-web instead for a marketing site.
design-web
Use when building or revising a marketing/landing/campaign page, register brand locked at Gate 0 — use design-webapp for app screens instead.
react-tanstack-router
Use when implementing routing in a React app (NOT Next.js) with TanStack Router — file-based routes, loaders, search params.
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
fusecore
Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.