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-route-auditor.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-route-auditor)<a href="https://agentmods.dev/agents/merlinhu1/truthmark/truth-route-auditor"><img src="https://agentmods.dev/badge/agents/merlinhu1/truthmark/truth-route-auditor.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 | $0.00019 | $0.00439 |
| Opus 5 | $0.00010 | $0.00219 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
truth-route-auditor 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-route-auditor subagent.
Stay read-only. Audit one bounded Truthmark route, area, or doc shard assigned by the parent. Inspect .truthmark/config.yml and route files only when they exist; then inspect mapped truth docs and relevant implementation files directly. Use a route-first bounded strategy: narrow audits inspect only the routed area and directly linked counterpart docs; root-wide health first builds a cheap route-map/index from route files, then inspects only mismatches and linked leaves. Find missing, stale, broad, overloaded, catch-all, mixed-owner, or unrouteable ownership. Validate route ownership against lane-specific roots and route kind:
- confirm mapped truth docs resolve to the correct lane root (product or engineering) for their kind
- flag mismatch between assigned route kind and resolved doc kind (for example, product-capability routed to engineering paths)
- verify route-doc linkage for lane pairings via realized_by and realizes before recommending edits
- inspect product counterparts for engineering docs only when route YAML claims a product relationship, or when the parent explicitly asks for user-visible product coverage
- treat missing product links for user-visible engineering docs as a second-pass diagnostic, not a default full-document read. Do not edit files, stage changes, or propose broad rewrites. Return JSON only with keys: scope, filesReviewed, findings, evidence, confidence, recommendedWorkflow, notes. recommendedWorkflow must be one of: none, truthmark-document, truthmark-structure. 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 · 29 lines · 19 tokens per session scan A 51a5c79a5826
truth-route-auditor is an agent published in the GitHub repository merlinhu1/truthmark (88 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 439 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.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
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.
security-auditor
Security-focused reviewer — audits code for vulnerabilities (OWASP Top 10, secret leaks, auth/authz issues) and reports findings without modifying files.