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 tmusser/ai-engineering-skills --skill ship-minigit clone --depth 1 https://github.com/tmusser/ai-engineering-skillsWrote 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/tmusser/ai-engineering-skills/ship-mini)<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/ship-mini"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/ship-mini/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/tmusser/ai-engineering-skills/ship-mini"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/ship-mini.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 | $0.00037 | $0.00974 |
| Opus 5 | $0.00018 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
ship-mini 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 9d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship Mini
Purpose
Decide whether verified work is safe and authorized to activate in a real operating environment.
verify-contract owns correctness and evidence. ship-mini does not re-verify the implementation; it owns the additional operational question: should this verified thing be allowed to act on the world now?
When to use
Use after verification when activation introduces one or more material operational risks:
- production or shared-state writes
- scheduled, autonomous, or unattended execution
- sending, publishing, triggering jobs, or other external side effects
- new or expanded tool permissions
- secrets, credentials, PII, or sensitive-data access
- destructive or difficult-to-reverse actions
- a required human approval boundary
- a meaningful rollback, audit, or owner-notification requirement
Skip ship-mini for ordinary local or interactive changes whose effects remain reviewable and reversible. A user-facing change, shared report, dashboard update, model result, or successful verify-contract does not require ship-mini merely because it may be released or seen by others.
Do not create SHIP.md when no material activation risk exists.
Inputs
VERIFY.mdstatus and evidence reference- What will be activated and where
- Allowed tools / actions
- Forbidden tools / actions
- Target environment or shared state
- Destructive or irreversible operations
- Secrets, credentials, PII, or sensitive-data scope
- Dry-run or staged activation path when relevant
- Human approval gates
- Audit logging
- Rollback / disable path
- Owner notification
- Stop conditions
Workflow
- Confirm the implementation already has sufficient verification evidence. Reference
VERIFY.md; do not replay correctness checks merely becauseship-miniis invoked. - Classify activation risk:
NONE— no material side effect, autonomy, permission, data, or rollback boundary exists. Stop without creatingSHIP.md.PRESENT— one or more material activation risks exist. Continue.
- Name the exact activation surface: what will run, write, send, publish, trigger, access, or mutate, and in which environment.
- Record allowed and forbidden actions, permission/data boundaries, destructive operations, and required human gates.
- Confirm the smallest practical dry-run or staged activation path when one exists.
- Confirm rollback or disable path before irreversible or shared-state effects are enabled.
- Confirm audit logging, owner notification, and stop conditions when unattended or externally visible effects are possible.
- Resolve any
REVIEW_REQUIREDverification item that affects activation safety. A functionalFAILcannot be shipped. - Create or update
SHIP.mdwith the activation decision and only the operational evidence needed forGO/NO-GO.
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.
- 9d ago First seen · 103 lines · 37 tokens per session scan A 8598edf97c33
ship-mini is a skill published in the GitHub repository tmusser/ai-engineering-skills (4 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 974 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 2026-08-31.
Other skills, from other repositories
awsl
Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.
dwi-all-in-one
Apply the relevant Dwi lenses together when several observed workflow problems co-occur. Select only the lenses the task needs, preserve a silent fast path for clear reversible work, and keep authority and evidence explicit. Prefer a focused module when one issue dominates.
dwi-arc
Structure genuinely multi-agent coding work into bounded cells with one writer per scope, explicit integration, and independent review. Use when several disjoint workstreams justify coordination. Do not use for small tasks, overlapping writers, speculative agent fleets, or process artifacts without demonstrated value.
dwi-bridge
Coordinate bounded work between native Claude and Codex workflows with explicit authority, scope, and evidence. Use for read-only consultation or explicitly authorized execution delegation. Do not create a new connector, share secrets, treat messages as authorization, or allow recursive delegation.
dwi-budget
Set and report practical token, context, time, tool-call, and coordination boundaries for coding-agent work. Use when resource use is unclear or needs a checkpoint. Do not invent measurements, monetary savings, cache benefit, or precision that the harness does not expose.
dwi-evidence
Label coding-agent claims by evidence status, preserve provenance and failures, and separate static, runtime, and human proof. Use before completion, comparison, promotion, or handoff. Do not upgrade observations into guarantees or fabricate missing measurements and approvals.