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 agentmods add skills/mtthsnc/tempest/shipnpx skills add mtthsnc/tempest --skill shipgit clone --depth 1 https://github.com/mtthsnc/tempestWhat 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 | $0.00080 | $0.00749 |
| Opus 5 | $0.00040 | $0.00375 |
| Sonnet 5 | $0.00016 | $0.00150 |
| Haiku 4.5 | $0.00008 | $0.00075 |
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 2d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ship — land a reviewed change cleanly
Overview
The loading dock. Take a change that has already been reviewed and get it out the door without surprises: tests in place, changelog updated, an honest PR description, CI green, and the deploy actually verified — not just assumed. Shipping is outward-facing and often irreversible, so the bar is "proven in the world," not "merged."
This is a STARTER skill — a generic spine. Rewrite the procedure below to encode your own release process: your CI provider, your changelog format, your deploy and rollback commands.
You do not build or re-review here. The change is done; your job is to land it safely.
Procedure
1. Confirm it's ready to ship
- Verify the change has been reviewed and the working tree is clean — no stray edits, no debug code.
- Confirm the diff is one coherent change. If unrelated work has crept in, split it out; ship one thing at a time.
2. Tests and changelog
- Ensure tests cover the change and the full suite passes locally. A green local run is the floor.
- Add a changelog entry for any user-facing change — what changed, in the user's words.
3. Write a tight PR description
- What changed, in one or two sentences.
- Why — the problem it solves or the reason it's worth shipping.
- How verified — the exact tests run and behavior observed. Name the risk honestly; don't bury it.
4. Open the PR (or land) and wait for CI
- Push and open the PR (or land, per your flow). Watch CI to completion.
- If CI is red or skipped, stop and fix the cause — never override or merge around it.
5. Verify the deploy end-to-end
- After merge/release, confirm the deploy itself works: hit the running service, check the version, observe the new behavior in the real environment. CI passing is not the deploy working.
- If it's broken, roll back first, diagnose second.
6. Record what shipped
- Note the version/PR/commit and what it delivered. Close the loop with whoever was waiting on it.
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.
- 2d ago First seen · 61 lines · 0 tokens per session scan A a840ddc0ef8f
ship is a skill published in the GitHub repository mtthsnc/tempest (2 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 749 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
pi-ralph-wiggum
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.
improvement-discovery
Heuristics and process for discovering structural improvements in this package. Load when planning a new improvement round — contains the smell taxonomy, analysis workflow, and prioritization framework distilled from many phases of refactoring.
markdown-conventions
Project-specific markdown rules (one-sentence-per-line, compact tables, sequential numbering) and YAML frontmatter schema for plans/retros. Load when writing or editing markdown — contains rules that differ from standard markdownlint defaults.
fabric-supervisor
Starts a persistent Pi Fabric supervisor that watches the main session toward a concrete goal and steers only when needed. Use for long-running goal supervision without another extension.
pre-completion
Pre-completion protocol for implementation agents — gather context, dispatch the pre-completion-reviewer subagent, and handle its report before writing stage notes and recommending /ship-issue. Load at the end of /tdd-plan and /build-plan after all implementation steps are complete.
prose-review
Review prose written for others -- user-facing docs, prompts for other LLMs, inline comments, docstrings, and other-facing messages -- for local jargon leakage, orphaned references, missing grounding, and audience or genre misfit.