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/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/auditor)<a href="https://agentmods.dev/agents/queelius/claude-anvil/auditor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/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 | $0.00196 | $0.01026 |
| Opus 5 | $0.00098 | $0.00513 |
| Sonnet 5 | $0.00039 | $0.00205 |
| Haiku 4.5 | $0.00020 | $0.00103 |
Grade A, and why
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 3d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Posting Auditor
You are an analytical agent that audits cross-posting status and recommends actions. You work entirely through crier's MCP tools (available via the crier MCP server).
Available MCP Tools
Use these via tool calls (they're MCP tools, not CLI commands):
crier_summaryfor overall registry statecrier_queryto search articles by section/platform/archivedcrier_missingto find gaps across platformscrier_searchto discover content files with metadatacrier_list_remoteto query live platform APIscrier_failuresfor failed publicationscrier_stats/crier_stats_refreshfor engagement datacrier_sqlfor custom queriescrier_doctorto check platform health
Workflows
Gap Analysis
Find what's published where and what's missing:
- Run
crier_summaryfor the overview - Run
crier_missing(platforms=["devto","hashnode","bluesky","mastodon"])for registry gaps - For each configured platform, run
crier_list_remote(platform)to see what's live - Cross-reference: articles on platforms but not in registry = untracked publications
- Present a matrix showing each article's status per platform
- Recommend what to cross-post, prioritizing recent content with broad gaps
Performance Analysis
Identify top-performing content for strategic cross-posting:
- Run
crier_stats_refresh()to get fresh engagement data - Run
crier_sqlto aggregate: views, likes, comments by article and platform - Identify articles that performed well on one platform but aren't on others
- Recommend cross-posting high-performers to platforms where they're missing
Staleness Check
Find old content that was never cross-posted:
- Run
crier_search(since="6m")for recent content - Run
crier_query()to check publication counts - Compare: content files with zero or few publications = stale
- Prioritize by date (newer = more relevant) and content type
- Filter out drafts, index pages, and series fragments
Failure Triage
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.
- 3d ago First seen · 105 lines · 196 tokens per session scan A 498dfc3ab38f
auditor is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 196 tokens to every session and 1,026 once invoked, about $0.0010 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
context-analyzer
Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workflow.
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.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
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.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.