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 adamdaw/claude-code-skills --skill claims-verifiergit clone --depth 1 https://github.com/adamdaw/claude-code-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/adamdaw/claude-code-skills/claims-verifier)<a href="https://agentmods.dev/skills/adamdaw/claude-code-skills/claims-verifier"><img src="https://agentmods.dev/badge/skills/adamdaw/claude-code-skills/claims-verifier.svg" alt="Measured on agentmods" 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 | $0.00137 | $0.38137 |
| Opus 5 | $0.00068 | $0.19068 |
| Sonnet 5 | $0.00027 | $0.07627 |
| Haiku 4.5 | $0.00014 | $0.03814 |
Grade A, and why
claims-verifier 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 — 2,505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claims verifier
One cold adversarial pass over a document, claim by claim. The reviewer is a fresh subagent invocation; it attempts to refute every factual and logical claim and returns a verdict for each. Nothing is edited in a pass — revision happens only through the author's dispositions between passes. The skill is self-contained: the standards it enforces are stated here rather than delegated to a guide.
Partner to senior-code-review: that skill holds code to the craft, this one holds
prose to its evidence. The burden of proof sits with the document — a claim stands
because a cited source carries it, or because it follows validly from supported
premises, never because it sounds right. The line holds even for commonplaces: an
unsourced truism is still UNSUPPORTED, and the author retires it with a disposition
rather than the adversary waving it through on shared knowledge.
Throughout, the author is the human who owns the document and declares the review converged; the orchestrator is the session running this loop.
Contents
- Why a subagent and not this session (46) — the structural-independence rule.
- Inputs the adversary gets (58) — source-list entry forms, identity line, standing section.
- Where the record lives (224) —
claims-review.md; the three content kinds. - One hash identity (335) — the three spawn hashes; the content-addressed snapshot store.
- Running requirements (364) — the
claims-auditoragent to install; the assurance ladder (sealed · quarantined-clone · adversary-only). - The loop (431)
-
- Resolve inputs, check them, assurance preflight (433)
-
- Audit the pass — the seven checks (501): Coverage, Attestations, Segmentation, Support, Reconciliation, Stability, Merits (655+)
-
- Work the findings — fix / accept / reject / contest (1181)
-
- UNVERIFIABLE → author fetch (1376)
-
- Apply fixes, run the next pass (1390)
-
- Converged — predicates, streak, declaration, certification invocation, cross-party draw (1392)
-
- Running a pass (1620) — spawn shape; the verbatim adversary prompt follows (1649).
- Read fence (1652) · What counts as a claim (1894) · Procedure (2033) · Hard prohibitions (2283) · Output (2301: Source check 2324, Claim ledger 2353, Support record 2371, Findings 2388, Observations 2411)
- Terms (2424) — glossary of the coined load-bearing terms.
- Limits (2452) — what the audits do and do not catch.
- Related (2494).
What ships with it
2 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.
- 8d ago First seen · 2,505 lines · 137 tokens per session scan A 0854667be5c7
claims-verifier is a skill published in the GitHub repository adamdaw/claude-code-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 137 tokens to every session and 38,137 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…