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-productgit 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-product)<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/repo-harness-product"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-product/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-product"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-product.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 | $0.00030 | $0.00358 |
| Opus 5 | $0.00015 | $0.00179 |
| Sonnet 5 | $0.00006 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
repo-harness-product scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
repo-harness-product
Canonical rule owner for PRD, Sprint, and Goal. Router-only: shared
preflight, mode selection, and cross-mode boundaries. Mode protocol lives
under references/.
Shared Preflight
- Confirm the working repo with
git rev-parse --show-toplevel. - Read
docs/spec.mdand.ai/harness/policy.jsonwhen present.
Mode Selection
- A product idea needs an upper-layer PRD ->
references/prd.md. - A PRD or spec needs an ordered Sprint backlog, or a Sprint task needs to run or report status ->
references/sprint.md. - A detailed PRD/Sprint needs a bounded native
/goalsession ->references/goal.md.
Boundaries
- Approval gating: no mode sets
> **Status**: Approved, or bypasses$think,repo-harness run capture-plan, task contracts,/check, or external acceptance on the user's behalf; explicit human approval always precedes implementation. tasks/todos.mdis the deferred-goal ledger only; no mode treats it as an active backlog or goal queue.- Product planning does not install or imply ChatGPT; ChatGPT surfaces are discovered only through their own explicit setup.
- None of these modes implements backlog tasks itself; work flows through the existing plan -> contract -> worktree -> verify gates.
What ships with it
3 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.
- 13d ago First seen · 30 lines · 30 tokens per session scan A af93f55a4470
repo-harness-product is a skill published in the GitHub repository Ancienttwo/repo-harness (431 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 358 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
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
mastermind-project-history
Retrieve and reason from durable project decisions, failed approaches, audits, reports, and lessons without treating provenance, search rank, or user approval as technical proof. Use when asking why a design exists, whether an approach was tried, what supersedes an older decision, what prior evidence should constrain…
mastermind-task-executor
Execute an approved Mastermind task contract within Scope, prove its Acceptance Criteria, and write the canonical file-backed executor report. Use when the user hands off a .mastermind/tasks/ - /spec.md or explicitly asks to execute an approved Mastermind task.
aidex-backlog
Use when the user wants to capture or defer something for later without acting on it now, or to work the existing backlog as a board. Fires on "add to the backlog", "add to the backlog the idea of X", "park this for later", "defer this one", "shelve the X idea", "queue this for later", "track this for later", "we'll…
aidex-request
Use when the user relays an incoming stakeholder, client, or product request that should be captured as a written .context/requests/ item before anyone acts on it — a feature ask, a requirement from a meeting, user feedback to formalize. Fires on "the client asked for X", "the stakeholder wants X", "capture this as a…
aidex-plan-exec
Use when the user asks to execute, implement, or continue a written multi-phase plan — typically a .context/plans/ document or any plan with checkboxes/phases. Fires on "implement the plan", "execute plan X", "let's execute the plan", "continue with phase Y", "resume the plan", "run the plan phase by phase". Enforces…