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-setupgit 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-setup)<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/repo-harness-setup"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-setup/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-setup"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-setup.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 | $0.00034 | $0.00420 |
| Opus 5 | $0.00017 | $0.00210 |
| Sonnet 5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
repo-harness-setup 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 11d 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.
What it actually says
repo-harness-setup
Canonical rule owner for init, migrate, upgrade, repair, scaffold, and
capability configuration. Router-only: shared preflight, mode selection, and
cross-mode boundaries. Mode protocol lives under references/.
Shared Preflight
- Confirm the target repo path (
pwd, or an explicit--repoargument). - Run
bun scripts/inspect-project-state.ts --repo <repo> --format textwhen available.
Mode Selection
- No harness yet, or refreshing an existing install ->
references/init.md. - Inspector reports legacy docs or stale harness artifacts ->
references/migrate.md. - Harness present, needs latest contract/helpers/templates ->
references/upgrade.md. - A specific workflow surface is broken ->
references/repair.md. - New project/app/module skeleton, no existing repo workflow ->
references/scaffold.md. - Add or sync one capability boundary only ->
references/capability.md.
Boundaries
- Never write user-level (
HOME) state from a repo-scoped mode; user-level setup is the separaterepo-harness updatecommand. - Preserve user-authored repo files unless the workflow contract owns the generated surface; remove only
ownership=known_generatedfiles. - Does not create an application stack from any mode except
scaffold. - Does not expose internal helper scripts (
create-project-dirs, directscripts/init-project.sh,hooks-init,docs-init) as public commands. - Does not infer capability prefixes from broad directory globs; always use explicit prefixes.
- A request spanning more than one mode resolves in dependency order, re-running the shared preflight before each next mode.
What ships with it
6 files 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.
- 11d ago First seen · 35 lines · 34 tokens per session scan A ae1f444cdf4a
repo-harness-setup is a skill published in the GitHub repository Ancienttwo/repo-harness (431 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 420 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
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-plan-refactor
Identify a high-priority refactoring target, assess its blast radius, and write .openlore/refactor-plan.md without changing code. Use when asked to plan or prioritize a refactor.
openlore-debug
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
openlore-implement-story
Implement a brownfield story with OpenLore orientation, risk checks, spec validation, tests, and drift detection. Use when asked to implement or continue a story in an existing codebase.
openlore-write-tests
Write and run real tests for a function or spec scenario after reading implementation and contract evidence. Use when asked to add, improve, or repair tests without stubs or placeholders.