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-shipgit 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-ship)<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/repo-harness-ship"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-ship/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-ship"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 32 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00295 |
| Opus 5.5 | $0.00014 | $0.00118 |
| Sonnet 5.5 | $0.00007 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
repo-harness-ship 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 4d 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-ship
Bot entrypoint. Confirm the exact publication and cleanup authorization.
Assign Git/PR steps through references/worker.md. Consume the recorded checks,
revision and independent review when risk requires it. Preserve unrelated work.
Main publication, deletion, credentials/permissions and release/production have separate boundaries. Merge only when this task authorizes main publication, automated checks pass and GitHub has no change request or unresolved review thread that a person started. A review bot thread is advisory. An explicit no-merge instruction wins. Record the squash commit, its revert command and the daily report after authorized publication.
The paragraph above is the internal PR flow. Classify each PR with the
repo-harness-check reference references/pr-verification.md. An external PR
never uses the internal flow. It merges only with a current verification bundle,
passing automated checks and the owner's explicit GO for the reviewed head SHA.
An internal tasks/lessons.md change also needs that GO.
Auto-delete only merged, clean worktrees/branches. Ask for other deletion.
Return PR URL, head SHA, verification, risk and rollback.
What ships with it
2 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.
- 4d ago Changed · +1 lines 6a30af395e47
- 24d ago Changed · +6 lines 71f35108d671
- 1mo ago Changed · -16 lines · -5 tokens per session 5bf286937770
- 2mo ago First seen · 37 lines · 39 tokens per session scan A 59926ef29068
repo-harness-ship is a skill published in the GitHub repository Ancienttwo/repo-harness (435 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 295 once invoked, about $0.0001 per session on Opus 5.5. 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.
repo-harness-ship compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-harness-shipAncienttwo/repo-harness | Skill | 435 | yesterday | MIT | A | 34 | Claude Code, Codex |
| release-sidecarmarcus/sidecar | Skill | 1.1k | 29d ago | MIT | A | 53 | Claude Code |
| releasearcee-ai/nac | Skill | 296 | yesterday | Apache-2.0 | A | 53 | Codex |
| graincrawlvincentkoc/dotskills | Skill | 111 | yesterday | MIT | A | 47 | Codex |
| crawlkitvincentkoc/dotskills | Skill | 111 | yesterday | MIT | A | 30 | Codex |
| hyalo-changelogractive/hyalo | Skill | 27 | today | MIT | A | 24 | Codex |
| safe-public-releaseserejaris/personal-corp-os | Skill | 241 | 3d ago | MIT | C | 166 | Claude Code |