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 epicsagas/epic-harness --skill shipgit clone --depth 1 https://github.com/epicsagas/epic-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/epicsagas/epic-harness/ship)<a href="https://agentmods.dev/skills/epicsagas/epic-harness/ship"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-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/epicsagas/epic-harness/ship"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/ship.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 | $0.00037 | $0.00814 |
| Opus 5.5 | $0.00015 | $0.00326 |
| Sonnet 5.5 | $0.00007 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship — Ship It
CRITICAL: Run HARNESS_DIR=$(epic-harness path) first. NEVER use .harness/ in the project directory.
Process
Step 0: Prerequisites
Load the spec for PR content:
ls -t $HARNESS_DIR/specs/SPEC-*.md | head -1
Gate: audit must have passed. If no audit report exists, invoke the audit skill before continuing.
Step 1: Pre-ship Verification
1a. Isolated Integration Test
Launch an agent with isolation: "worktree" to verify in a clean environment:
- Run full build from scratch (
cargo build --release/npm run build/ etc.) - Run complete test suite
- Run linter and formatter checks
- Verify no uncommitted artifacts
Gate: If isolated test fails → STOP. "Fix with /go, then re-run /audit before shipping."
Step 2: Git Hygiene
- Ensure all changes are committed (Conventional Commits)
- Rebase on latest base branch if needed
- Squash fixup commits if appropriate
Step 3: Create PR
gh pr create --title "<goal from spec>" --body "$(cat <<'EOF'
## Summary
<Goal from spec — what and why, not how>
## Spec
- Spec ID: SPEC-{timestamp}
- Requirements: R1, R2, ...
## Changes
<bullet list of key changes>
## Acceptance Criteria Verified
- AC1: ✅
- AC2: ✅
## Audit Report
<paste full Audit Report>
## Test Plan
- [ ] Unit tests pass
- [ ] Integration tests pass
- [ ] Manual verification done
EOF
)"
Register the PR in the merge-outcome ledger (orbit pipelines are picked up automatically; standalone ships need this one-liner):
epic-harness evolve record-pr <PR_URL> [--goal <goal_slug>] [--branch <branch>]
Step 4: CI Verification
gh pr checks <PR_NUMBER> --watch
If CI fails, diagnose and fix automatically. Retry up to 2 times.
Step 5: Report
## Ship Report
- Spec: SPEC-{timestamp} ({goal_slug})
- PR: <URL>
- CI: [PASS/FAIL/N/A]
- Ready to merge: [YES/NO]
- Action needed: <if any>
If inside /orbit: Return control to orbit — it will run evolve automatically.
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 Changed · +7 lines 9a92a9a8e2e7
- 1mo ago First seen · 112 lines · 37 tokens per session scan A 9328c912bd54
ship is a skill published in the GitHub repository epicsagas/epic-harness (20 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 814 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.
Other skills, from other repositories
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
github
GitHub CLI (gh) for repository management, issues, pull requests, releases, workflows, search, gists, and API access. Use when the user asks about any GitHub operation — creating repos, forking, cloning, PR workflows, issue triage, CI/CD runs, code search, release management, or direct API calls. Keywords: github, gh…
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
git
Run git version control commands for repository management. Use when the user asks to check status, view history or diffs, stage and commit changes, manage branches, merge or rebase, work with remotes, stash changes, tag releases, cherry-pick commits, bisect regressions, resolve conflicts, manage worktrees or…
pi-release-workflow
Use when preparing or validating Pi monorepo releases, including Changesets, pnpm lockfile updates, package previews, release-age policy, and installability checks.