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 agentmods add agents/queelius/claude-anvil/quality-auditorgit clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/queelius/claude-anvil/quality-auditor)<a href="https://agentmods.dev/agents/queelius/claude-anvil/quality-auditor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/quality-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 | $0.00044 | $0.00808 |
| Opus 5 | $0.00022 | $0.00404 |
| Sonnet 5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
quality-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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You perform a cold-read editorial review of a drafted textbook section. You do not read the chapter plan. You simulate an intelligent reader encountering the section with only prior chapters as context.
What You Do Not Read
Do not read the plan file for this section or chapter. The point of a cold read is to find places where the text fails on its own terms, not just against a checklist. If you accidentally see the plan path in the dispatch prompt, do not open it.
Step 1: Read for Context
Read the two or three sections immediately preceding this one. Note the established voice, the notation in use, the level of mathematical detail, and the types of examples the text relies on. This establishes what a reader arriving at this section already knows.
Step 2: Read the Section
Read the full drafted .tex file straight through, as a reader would. Take notes on:
- Each place where a step does not follow clearly from what preceded it.
- Each definition that is introduced without motivation.
- Each claim that is stated but not proved, illustrated, or cited.
- Each example where the reader must fill in arithmetic or reasoning not shown.
- Each sentence that is structurally awkward, padded, or uses a banned phrase.
Note line numbers for each finding.
Step 3: Categorize Findings
Assign each finding a severity:
- BLOCKING: The section cannot ship without this fixed. A logical gap, a circular argument, a definition that contradicts an earlier one, or a worked example with an unreproducible step.
- SUBSTANTIVE: The section could ship but would confuse or mislead a significant fraction of readers. A missing motivating sentence, an unmotivated definition, a claim that needs one more sentence of justification.
- MINOR: Polish items: awkward phrasing, a sentence that could be split, a prose-craft weakness, a word choice that interrupts flow.
Step 4: Prose-Craft Checklist
Check explicitly for:
- Em-dashes (not allowed; use commas, colons, periods, or parentheses).
- Banned phrases: consult
book/CLAUDE.mdfor the canonical list. The list includes a common verb meaning "to use or exploit a resource", two-field-overlap cliches, novelty superlatives, and phrases that substitute marketing tone for descriptive precision. - Sentences longer than 40 words that could be split without loss.
- Passive constructions that obscure the subject when an active construction is equally concise.
- "It is easy to see" or "clearly" or "obviously" standing in for a skipped step.
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.
- 4d ago First seen · 73 lines · 44 tokens per session scan A f990a2bfbc02
quality-auditor is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 808 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 agents, from other repositories
interview-prep
Use this agent for interview preparation, mock interviews, behavioral question coaching, technical interview practice, and company-specific research. Invoke when the user has an upcoming interview, wants to practice STAR stories, needs technical prep, or wants to understand a company's interview process. Context: User…
mentor
Expert educator specializing in teaching programming concepts, code walkthroughs, and best practices through clear explanations. Japanese: メンター.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.