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 wjgoarxiv/autoresearch-skill --skill shipgit clone --depth 1 https://github.com/wjgoarxiv/autoresearch-skillWrote 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/wjgoarxiv/autoresearch-skill/ship)<a href="https://agentmods.dev/skills/wjgoarxiv/autoresearch-skill/ship"><img src="https://agentmods.dev/badge/skills/wjgoarxiv/autoresearch-skill/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/wjgoarxiv/autoresearch-skill/ship"><img src="https://agentmods.dev/badge/skills/wjgoarxiv/autoresearch-skill/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00157 | $0.02014 |
| Opus 5 | $0.00078 | $0.01007 |
| Sonnet 5 | $0.00031 | $0.00403 |
| Haiku 4.5 | $0.00016 | $0.00201 |
Grade A, and why
autoresearch: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 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.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autoresearch:ship
Universal 8-phase shipping pipeline. Runs automatically through phases 1–6, pauses exactly
once at phase 7 for irreversible-action confirmation, then executes phase 8. Outputs
ship-log.md tracking every checklist item.
Autonomy Directive
You are an autonomous shipping agent. Once the pipeline begins:
- Run phases 1–6 without stopping. They are automated and reversible.
- Phase 7 is the ONLY pause point. You MUST stop and wait for explicit user approval before proceeding to phase 8.
- Never skip phase 7. Deploy/publish is irreversible. No exceptions.
- After phase 8, close the pipeline immediately — do not run additional phases.
Setup
Step 1 — Identify artifact type
Ask if not provided: "What are you shipping? Choose one: (1) library/package, (2) CLI tool, (3) REST API, (4) web app, (5) ML model/dataset, (6) skill/prompt, (7) documentation site, (8) infrastructure (IaC), (9) research paper/report"
Load the corresponding checklist from skills/ship/type-checklists.md.
Step 2 — Identify deploy target
Ask if not provided: "Where does this deploy? (e.g., PyPI, npm, GitHub Releases, Vercel, AWS, HuggingFace, arXiv...)"
Step 3 — Initialize ship-log.md
Write ship-log.md to the working directory with the artifact type, deploy target, and
timestamp. All 8 phases will be appended as they execute.
The 8-Phase Pipeline
Phase 1 — Verify Completeness
Check that all required files exist and no critical placeholders remain:
- Core source files present
- No
TODO,FIXME,PLACEHOLDER, orTBDin production code paths - Required config files present (e.g.,
pyproject.toml,package.json,Dockerfile) - All checklist items from type-checklists.md for this type are present
Log each check as PASS or FAIL in ship-log.md. A single FAIL here is a blocker —
fix it before proceeding to phase 2.
Phase 2 — Run Full Test Suite
Execute the test suite. Wrap with timeout 10m <test_command>.
- All tests must pass. Zero failures, zero errors.
- Flaky tests that fail must be investigated — not skipped.
- If no test suite exists: log
WARNING — no tests found. Continue, but flag in ship-log.md.
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.
- 11d ago First seen · 215 lines · 157 tokens per session scan A 053a6beaa249
autoresearch:ship is a skill published in the GitHub repository wjgoarxiv/autoresearch-skill (32 stars, last pushed 2mo ago), licensed MIT. It adds 157 tokens to every session and 2,014 once invoked, about $0.0008 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
land-and-deploy
Land and deploy workflow. (gstack).
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
cs-ending-time
Use when the user asks to finish, ship, publish, commit, push, or deploy a completed implementation in one bounded delivery scope.
deploy
Deploy latest master to production with a version tag. Use when releasing to production or tagging a deploy.
land-and-deploy
Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack).
ship
Use when code is ready to ship — creates PRs, merges, deploys, and verifies. Handles the full PR-to-production pipeline. Triggers on /ship.