ECC is a toolkit that organizes and improves how coding agents work through skills, memory, security checks, research practices, and related extensions. It is for developers using agents such as Claude Code, Codex, OpenCode, and Cursor.
Borrowing it
Nothing to install: this file belongs to affaan-m/ECC. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/affaan-m/ECC/main/.opencode/commands/harness-audit.mdgit clone --depth 1 https://github.com/affaan-m/ECCWrote 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/commands/affaan-m/ecc/harness-audit)<a href="https://agentmods.dev/commands/affaan-m/ecc/harness-audit"><img src="https://agentmods.dev/badge/commands/affaan-m/ecc/harness-audit/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.
<a href="https://agentmods.dev/commands/affaan-m/ecc/harness-audit"><img src="https://agentmods.dev/badge/commands/affaan-m/ecc/harness-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.00752 |
| Opus 5 | $0.00006 | $0.00376 |
| Sonnet 5 | $0.00003 | $0.00150 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
harness-audit 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 5d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Audit Command
Run a deterministic repository harness audit and return a prioritized scorecard.
Usage
/harness-audit [scope] [--format text|json] [--root path]
scope(optional):repo(default),hooks,skills,commands,agents--format: output style (textdefault,jsonfor automation)--root: audit a specific path instead of the current working directory
Deterministic Engine
Always run:
node scripts/harness-audit.js <scope> --format <text|json> [--root <path>]
This script is the source of truth for scoring and checks. Do not invent additional dimensions or ad-hoc points.
Rubric version: 2026-05-19.
The script computes up to 12 fixed categories (0-10 normalized each). The first seven are always applicable; GitHub Integration is always applicable; deploy-target categories are applicable only when a matching marker is detected.
- Tool Coverage
- Context Efficiency
- Quality Gates
- Memory Persistence
- Eval Coverage
- Security Guardrails
- Cost Efficiency
- GitHub Integration
- Vercel Integration (when
vercel.jsonor.vercel/is present) - Netlify Integration (when
netlify.tomlor.netlify/is present) - Cloudflare Integration (when
wrangler.tomlorwrangler.jsoncis present) - Fly Integration (when
fly.tomlis present)
Scores are derived from explicit file/rule checks and are reproducible for the same commit. The script audits the current working directory by default and auto-detects whether the target is the ECC repo itself or a consumer project using ECC.
Output Contract
Return:
overall_scoreout ofmax_score.max_scoredepends on which categories are applicable to the target; never assume a fixed total.applicable_categories[]andcategory_countdescribing which categories contributed.- Category scores and concrete findings.
- Failed checks with exact file paths.
- Top 3 actions from the deterministic output (
top_actions). - Suggested ECC skills to apply next.
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.
- 5d ago First seen · 85 lines · 13 tokens per session scan A 8fb765c7fbad
harness-audit is a command published in the GitHub repository affaan-m/ECC (254,593 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 752 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
amend-plan
Plan Amend - Discuss and apply amendments to a plan.json implementation plan.
export-closedloop-learnings
Exports pending ClosedLoop learnings to global location with deduplication.
goal-stats
Analyzes goal performance across runs, showing pass rates, pattern effectiveness, and improvement trends.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
design-inventory
Run the Claude Design to ClosedLoop pipeline: Stage A inventories a design export zip into schema-validated findings and publishes a platform Design Review document; Stage B is human review; Stage C derives decisions from the edited document and generates DRAFT feature tickets.
cancel-code
Cancel active ClosedLoop Loop.