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/qinghui316/ecl-harness-engineer/auditorgit clone --depth 1 https://github.com/qinghui316/ecl-harness-engineerWrote 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/qinghui316/ecl-harness-engineer/auditor)<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>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 | $0.00000 | $0.01614 |
| Opus 5 | $0.00000 | $0.00807 |
| Sonnet 5 | $0.00000 | $0.00323 |
| Haiku 4.5 | $0.00000 | $0.00161 |
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.
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.
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.
- yesterday Changed · -58 lines e46947ee0c61
- 5d ago First seen · 218 lines · 0 tokens per session scan A f902d154fc05
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.