Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sifxprime/kodelyth-eccnpx agentmods add commands/sifxprime/kodelyth-ecc/harness-auditWrote 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/sifxprime/kodelyth-ecc/harness-audit)<a href="https://agentmods.dev/commands/sifxprime/kodelyth-ecc/harness-audit"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-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/sifxprime/kodelyth-ecc/harness-audit"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-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 | $0.00014 | $0.00602 |
| Opus 5.5 | $0.00006 | $0.00241 |
| Sonnet 5.5 | $0.00003 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
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 1mo 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.
This is a copy
81% identical to harness-audit — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 78 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: 2026-03-30.
The script computes 7 fixed categories (0-10 normalized each):
- Tool Coverage
- Context Efficiency
- Quality Gates
- Memory Persistence
- Eval Coverage
- Security Guardrails
- Cost Efficiency
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(70 forrepo; smaller for scoped audits)- 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
Checklist
- Use script output directly; do not rescore manually.
- If
--format jsonis requested, return the script JSON unchanged. - If text is requested, summarize failing checks and top actions.
- Include exact file paths from
checks[]andtop_actions[].
Example Result
Harness Audit (repo): 66/70
- Tool Coverage: 10/10 (10/10 pts)
- Context Efficiency: 9/10 (9/10 pts)
- Quality Gates: 10/10 (10/10 pts)
Top 3 Actions:
1) [Security Guardrails] Add prompt/tool preflight security guards in hooks/hooks.json. (hooks/hooks.json)
2) [Tool Coverage] Sync commands/harness-audit.md and .opencode/commands/harness-audit.md. (.opencode/commands/harness-audit.md)
3) [Eval Coverage] Increase automated test coverage across scripts/hooks/lib. (tests/)
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.
- 1mo ago First seen · 78 lines · 14 tokens per session scan A 303c060c56e0
harness-audit is a command published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 20d ago), licensed MIT. It adds 14 tokens to every session and 602 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 81% identical to harness-audit, differing in 12 lines, and is treated as a copy.
Other commands, from other repositories
toh-help
Display all Toh Framework commands and quick usage guide.
learn
Analyze the current session and extract any patterns worth saving as skills.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.