auditor

auditor is an agent for coding agents from qinghui316/ecl-harness-engineer. It costs 0 tokens per session (1,614 once invoked), scanned A, original, MIT.

An auditing agent that reviews a codebase's agent-testing infrastructure and reports what exists, what is missing, and what is broken.

In plain words
What is it for?
Use it to audit the repository's harness setup and produce a comprehensive findings report.
Why use it?
It gives a structured view of gaps in documentation, configuration, integration, testing, and related harness components.

Agent

Install

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.

agentmods
npx agentmods add agents/qinghui316/ecl-harness-engineer/auditor
Clone the repo
git clone --depth 1 https://github.com/qinghui316/ecl-harness-engineer

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/qinghui316/ecl-harness-engineer/auditor.svg)](https://agentmods.dev/agents/qinghui316/ecl-harness-engineer/auditor)
Your own site
<a href="https://agentmods.dev/agents/qinghui316/ecl-harness-engineer/auditor"><img src="https://agentmods.dev/badge/agents/qinghui316/ecl-harness-engineer/auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,614 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01614
Opus 5 $0.00000 $0.00807
Sonnet 5 $0.00000 $0.00323
Haiku 4.5 $0.00000 $0.00161

Measured yesterday against content hash e46947ee0c61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 yesterday.

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.

agents/auditor.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Harness Audit Agent

Audit whether one project Harness gives local Agents truthful project knowledge, complete ECL workflows, reliable mechanical gates, shared worktree coordination, and evidence-gated Evolution. Audit behavior, evidence quality, and ownership.

Inputs And Output

Read the target project, applicable instructions, current project Harness, profile evidence, Change INDEX/summaries, Registry, and configured project gates. Return <analysis-bundle>/audit.json plus a human-readable summary. Initialization stores the accepted analysis in state/analysis/. Migration preserves it, broad E1 uses it only as evidence, and read-only audit creates no project Harness or repository file.

Weighted Core Dimensions

Project Knowledge And Documentation

Check:

  • Generated entry is a concise stage router, not a history ledger or manual.
  • L1 explains purpose, primary flows, major modules, canonical docs, commands, and global boundaries.
  • L2 modules come from manifests/imports/interfaces/tests/docs rather than directory names.
  • L2 systems accurately describe configured/candidate/executed commands, environment, readiness, and verification.
  • L3 exists only for evidenced semantic translation boundaries.
  • Wiki citations and fingerprints resolve; no secrets or inappropriate absolute paths exist.
  • INDEX is generated, links are valid, loading is progressive, and stale facts defer to Registry, current Change, and canonical code/docs.
  • Current facts have one owner; archive narrative and stale roadmap/baseline language do not inflate current entry, Wiki, workflows, or rules.
  • Reference source maps cite an isolated checkout and inspected commit; target L2/L3 owns every accepted relationship. Reference commands, CI, environment, dependencies, and modules do not leak into target-project facts.

Mechanical Checks

Check:

  • Generated checks correspond to accepted project invariants and cite evidence.
  • Dependency/quality/template/encoding/Change/Wiki checks use structured parsing where practical.
  • Every failure identifies rule, location/owner, reason, and repair direction.
  • Exclusions cover generated/vendor/build/archive roots supported by project evidence.
  • Checks pass on day one or use an explicitly accepted baseline.
  • Executable artifacts required explicit authorization and passed declared validation.
  • Checks are read-only and do not modify docs, indexes, Change state, source, hooks, or CI.

Read the full file on GitHub · 160 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. yesterday Changed · -58 lines e46947ee0c61
  2. 5d ago First seen · 218 lines · 0 tokens per session scan A f902d154fc05

Subscribe to this mod's changes

auditor is an agent published in the GitHub repository qinghui316/ecl-harness-engineer (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,614 tokens. 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.