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/raisedadead/claude-code-plugins/shipnpx skills add raisedadead/claude-code-plugins --skill shipgit clone --depth 1 https://github.com/raisedadead/claude-code-pluginsWhat 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 | $0.00102 | $0.01417 |
| Opus 5 | $0.00051 | $0.00709 |
| Sonnet 5 | $0.00020 | $0.00283 |
| Haiku 4.5 | $0.00010 | $0.00142 |
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 yesterday.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds:ship — changelog from the ledger, before the archive
Both plugin CHANGELOGs here hand-author dated wave entries; ds:ship mechanises that shape from §T plus git log. One file written, one recommendation printed, nothing else touched.
Inputs
--preview— allow a partial §T; print the draft to stdout and write nothing.--changelog <path>— explicit target file. Required whenever the repo holds more than oneCHANGELOG.md(this one holds two); the operator names the target. When a wave spans plugins, repeat per target with a row subset — the split derives from each cite's touched paths and the operator confirms it.
Steps
0. Detect host env
Per ADAPTERS.md.
1. Locate + gate
Live dossier per ds:status. A non-preview run requires §T all-x (the same scan ds:close uses). --preview skips the gate and only prints.
Changelog-target check: count CHANGELOG.md files in the repo (skipping node_modules/, .scratchpad/). More than one and no --changelog given → refuse:
ds:ship: <n> CHANGELOG.md files found — pass --changelog <path> (never guessing dispatch).
2. Resolve cites
For every x row, classify the cite cell first:
- SHA-shaped (
[0-9a-f]{7,40}): verify withgit -C <repo> cat-file -t <sha>per §X repo. A commit object resolves throughgit log -1 --format=... <sha>. Always pass the verified SHA — a baregit log -1 <cite>falls back to pathspec resolution and quietly resolves a wrong commit for non-SHA text. - Anything else (artifact filename, §-ref — FORMAT.md enumerates SHA/PR-ref/
—, and live dossiers legitimately carry artifact cites for research rows): bucket as[no commit cite], entry text from the ledger's task cell. A sanctioned no-commit row is signal, not noise. - SHA-shaped and present in no §X repo: flag
[cite unresolved]. Every row lands somewhere.
3. Parse + map
Conventional-commit regex on the subject (type(scope)!: desc). No match → bucket under Changed, flagged [non-conventional commit]. Map type → bump and type → category per reference/changelog-mapping.md (bump table = spec; category table = convention, labelled).
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.
- yesterday First seen · 93 lines · 102 tokens per session scan A ef17137a239c
ship is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 6d ago), licensed ISC. It adds 102 tokens to every session and 1,417 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…