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 skills add Ancienttwo/repo-harness --skill repo-harness-checkgit clone --depth 1 https://github.com/Ancienttwo/repo-harnessWrote 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/skills/ancienttwo/repo-harness/repo-harness-check)<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/repo-harness-check"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-check/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/skills/ancienttwo/repo-harness/repo-harness-check"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00874 |
| Opus 5 | $0.00018 | $0.00437 |
| Sonnet 5 | $0.00007 | $0.00175 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
repo-harness-check 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-harness-check
Use this command when the user asks whether the harness, migration, or release surface is ready.
Protocol
- Confirm the repo path and report dirty-worktree boundaries.
- Read the canonical required-check list from the target repo's root agent context (
CLAUDE.mdfor Claude,AGENTS.mdfor Codex)## Required Checkssection, then apply its scope conditions and run the applicable commands through the global/package helper runtime. This self-host source repo may also use rootscripts/for source-only maintenance commands. Use focused checks by default; a conditional full-suite command is not an unconditional requirement. Consume current canonical acceptance evidence for already-satisfied expensive criteria. After a bounded follow-up edit, have the parent retain the baseline full-run identity and revise final criteria to focused delta checks when no explicit full-suite requirement or uncovered integration risk remains; never relabel a baseline pass as current-subject full evidence. If## Required Checksis missing or empty, report that as the first blocking finding instead of substituting a default list. - Run advisory readiness when available:
repo-harness run check-agent-tooling --host both --json
- Treat missing CodeGraph or missing Codex
health/check/mermaidas hard failures. - Treat Waza staging drift as a yellow readiness flag; report the fix or acceptance reason without failing the repo gate.
- Report skill eval authority when release/readiness evidence depends on skill
effectiveness:
- authoritative: non-dry-run
bun run benchmark:skills --eval <slug>withfull_test_count > 0,dry_run_ratio <= 30%, and graders reported - non-authoritative: dry-run-heavy or all-dry-run evidence
- unavailable: no current eval evidence; report the benchmark command needed
- authoritative: non-dry-run
- Summarize pass/fail evidence, yellow flags, eval authority metrics, and the next blocking command if any.
Delegation Brief Evidence
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed 972688dd8f58
- 12d ago First seen · 48 lines · 36 tokens per session scan A 963365ff6d62
repo-harness-check is a skill published in the GitHub repository Ancienttwo/repo-harness (431 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 874 once invoked, about $0.0002 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.
Other skills, from other repositories
release
Cut and publish a full stable NAC release after main, release-PR, and publication CI pass. Use when a maintainer asks for a stable version bump, tag, or GitHub Release. Never use for release candidates; NAC RC releases are automated.
graincrawl
Maintain, verify, and release graincrawl, the local-first Granola archive CLI, including SQLite archive behavior, read-only Granola source boundaries, Homebrew tap packaging, and crawlkit-powered TUI/snapshot surfaces.
crawlkit
Maintain and release the crawlkit Go library, preserving downstream compatibility for gitcrawl, slacrawl, discrawl, and notcrawl.
ship
Ship phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.
transport-release-gate
Run a quality gate over an SAP transport request before it is released — collect the TR's objects, check for inactive objects and foreign locks, run syntax checks, ATC, and unit tests, then produce a structured go/no-go report. Use whenever the user wants to release a transport, asks "is this TR safe to release?"…
release-verification
A release-verification checklist for software versions and packages. It covers changelogs, tests, packaging, installation smoke checks, version-control actions, publishing, and checks after release.