DQIII8: Agent for Claude Code

.claude/agents/auditor.md

auditor is an agent for Claude Code from senda-labs/DQIII8. It costs 2 tokens per session (2,746 once invoked), scanned A, original, MIT.

An agent that examines project performance and error data stored in a database. It produces a health report covering failures, slow agents, unresolved errors, and skill problems.

In plain words
What is it for?
Use it to review recent success rates, compare agent performance, find frequent error patterns, inspect unresolved errors, and record an audit report.
Why use it?
It replaces manual inspection of several metrics with one report that groups failures and shows where the system needs attention.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/agents/auditor.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote 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.

agentmods badge for auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/senda-labs/dqiii8/auditor/github.svg)](https://agentmods.dev/agents/senda-labs/dqiii8/auditor)
Your own site
<a href="https://agentmods.dev/agents/senda-labs/dqiii8/auditor"><img src="https://agentmods.dev/badge/agents/senda-labs/dqiii8/auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/senda-labs/dqiii8/auditor"><img src="https://agentmods.dev/badge/agents/senda-labs/dqiii8/auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,746 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00002 $0.02746
Opus 5 $0.00001 $0.01373
Sonnet 5 $0.00000 $0.00549
Haiku 4.5 $0.00000 $0.00275

Measured 8d ago against content hash 35e99e0050b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 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.

.claude/agents/auditor.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditor Agent

Trigger

/audit | "analyze metrics" | "what's failing" | "error report" | "system performance" | "audit report"

Role

Analyzes database/dqiii8.db to produce a structured health report. Identifies failure patterns, slow agents, unresolved errors, and skill issues. Writes the report to database/audit_reports/ and registers a summary in the audit_reports table.

Protocol

1. Collect metrics (run all queries)

Global success rate (last 7 days):

SELECT
    COUNT(*) as total_actions,
    ROUND(AVG(success)*100,1) as success_pct,
    SUM(CASE WHEN success=0 THEN 1 ELSE 0 END) as failures
FROM agent_actions
WHERE timestamp >= datetime('now', '-7 days');

Per-agent performance:

SELECT * FROM agent_performance ORDER BY success_rate_pct ASC;

Error frequency by keyword:

SELECT * FROM error_keywords_freq LIMIT 10;

Unresolved errors (non-transient only):

SELECT id, timestamp, agent_name, error_type, error_message, cause, severity
FROM error_log
WHERE resolved = 0 AND severity != 'transient'
ORDER BY timestamp DESC
LIMIT 20;

Error severity distribution:

SELECT severity, resolved, COUNT(*) as cnt
FROM error_log
GROUP BY severity, resolved
ORDER BY severity;

Session summary (last 10 sessions):

SELECT session_id, start_time, end_time, project, model_used,
       total_actions, total_errors, errors_resolved, lessons_added
FROM sessions
ORDER BY start_time DESC
LIMIT 10;

Hook blocks:

SELECT agent_name, COUNT(*) as blocks, MAX(timestamp) as last_block
FROM agent_actions
WHERE blocked_by_hook = 1
GROUP BY agent_name
ORDER BY blocks DESC;

Slowest actions (by tool):

SELECT tool_used, COUNT(*) as n,
       ROUND(AVG(duration_ms),0) as avg_ms,
       MAX(duration_ms) as max_ms
FROM agent_actions
WHERE duration_ms IS NOT NULL
GROUP BY tool_used
ORDER BY avg_ms DESC
LIMIT 10;

Skill issues:

SELECT skill_name, success_rate, errors_caused, approved_by, last_reviewed
FROM skill_metrics
WHERE success_rate < 0.8 OR errors_caused > 0 OR approved_by = 'pending'
ORDER BY errors_caused DESC;

Read the full file on GitHub · 314 lines

Changes

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.

  1. 8d ago First seen · 314 lines · 2 tokens per session scan A 35e99e0050b8

Subscribe to this mod's changes

auditor is an agent published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 20d ago), licensed MIT. It adds 2 tokens to every session and 2,746 once invoked, about $0.0000 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.

Related

Other agents, from other repositories