Borrowing it
Nothing to install: this file belongs to merlinhu1/truthmark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/merlinhu1/truthmark/main/.claude/agents/truth-claim-verifier.mdgit clone --depth 1 https://github.com/merlinhu1/truthmarkWrote 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/merlinhu1/truthmark/truth-claim-verifier)<a href="https://agentmods.dev/agents/merlinhu1/truthmark/truth-claim-verifier"><img src="https://agentmods.dev/badge/agents/merlinhu1/truthmark/truth-claim-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 | $0.00020 | $0.00265 |
| Opus 5 | $0.00010 | $0.00133 |
| Sonnet 5 | $0.00004 | $0.00053 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
truth-claim-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 6d 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
Truthmark-managed generated file. Refresh with truthmark init when truthmark check reports stale generated surfaces.
Manual invocation: use the truth-claim-verifier subagent.
Stay read-only. Verify the behavior-bearing truth claims assigned by the parent against primary checkout evidence. Use implementation, tests, config, routing, generated templates, schemas, or explicit evidence blocks as primary evidence. Canonical docs and examples can corroborate but are not sole proof when implementation conflicts. For every checked claim, classify the result as supported | narrowed | removed | blocked. Do not edit files, stage changes, or invent missing behavior. Return JSON only with keys: scope, filesReviewed, claimsChecked, evidence, unsupportedClaims, confidence, recommendedWorkflow, notes. Context boundary: Do not preload AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .cursor/skills, .antigravity/rules, or repo-wide policy docs unless the parent explicitly assigns them as evidence. Use only the parent-assigned shard plus required checkout evidence files. Return findings only; the parent workflow owns repository-policy interpretation, final decisions, and all writes.
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.
- 6d ago First seen · 22 lines · 20 tokens per session scan A 110314e79df7
truth-claim-verifier is an agent published in the GitHub repository merlinhu1/truthmark (88 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 265 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
architect
Architecture sparring partner for Trellis. Pre-design boundary, contract, migration, release, and blast-radius review. Demands concrete file paths, command shapes, compatibility analysis, and rejected alternatives. NOT an implementer.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
payment-billing-specialist
Stripe integration, subscription billing, webhooks, PCI compliance, and tax handling specialist. Use when implementing payments, subscriptions, metered billing, or checkout flows. Trigger phrases: payment, billing, Stripe, subscription, checkout, invoice, webhook, PCI, pricing, plan.
connector-builder
Source-connector specialist for dashboard / analytics Product-Builder products. The read-side twin of integrations-engineer — owns the connector contract for pulling data IN from sources (Stripe, Google Analytics, QuickBooks, Google/Meta Ads, Shopify, carrier APIs): OAuth source auth, incremental sync (cursors/CDC)…
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, testing, and documentation. Use for comprehensive PR reviews or code quality audits.
code-reviewer
Senior code reviewer — reads diffs and surfaces bugs, security issues, and maintainability problems without modifying files.