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 OutlineDriven/odin-claude-plugin --skill review-and-shipgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/review-and-ship)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/review-and-ship"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/review-and-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/outlinedriven/odin-claude-plugin/review-and-ship"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/review-and-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 | $0.00038 | $0.01024 |
| Opus 5 | $0.00019 | $0.00512 |
| Sonnet 5 | $0.00008 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
review-and-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 5d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review and ship
Contract
| Field | Bound contract |
|---|---|
| Trigger | A human directly requests review and publication, or work passes the explicit signal authority: delegated. |
| Authority | Remote: pushes one branch and opens or updates one pull request; requires explicit human invocation. A route name or surrounding context never implies delegation; preview any credential, paid, data-at-rest, remote bulk, or irreversible consequence not already covered by that authority. |
| Side effect | Repairs the reviewed diff, creates local commits, pushes one branch without force, and opens or updates one pull request. |
| Done | No release-blocking finding remains, native checks pass, every intended commit is on the remote branch, and a confirmed pull-request URL is returned. |
Inputs
$AUTHORITY:directordelegated. Default todirectonly on direct human invocation.- The existing staged, unstaged, untracked, or already-committed diff.
- The repository's loaded Git, review, verification, and pull-request conventions.
- The publication remote, base branch, and head branch, resolved from repository state unless the caller supplied them.
Procedure
- Establish authority. Reject a delegated run without the literal
authority: delegatedsignal. Resolve the remote, base, head, and current HEAD. If HEAD is detached, attach it to a new publication branch named from the change. Do not change branches when that would discard or hide work. - Inspect the complete publication range and working tree. Include staged, unstaged, untracked, and ahead-of-remote commits. Exclude unrelated or sensitive files before review; never stage with a catch-all path.
- Review every changed file against behavior, security boundaries, repository rules, and scope. Repair actionable critical and high findings inside the requested change. Re-review each repaired region. Stop when a finding needs a product decision, destructive act, or scope increase that authority does not cover.
- Run the repository-native checks for every touched language and changed behavior. Fix source failures and repeat the affected check. Do not weaken, skip, or replace a configured gate to obtain green output.
- Package the working-tree diff into atomic commits. Split by reason for change, not by file count. Stage exact paths or exact hunks, apply the repository's message convention, and leave each commit buildable. Do not amend or rewrite existing history unless the human explicitly requested that separate operation.
- Fetch the publication remote. Classify the head as new, ahead-only, behind-only, or diverged against its remote branch. List the exact commits and checks that will publish. A behind-only or diverged branch blocks ordinary publication; never answer it with a force flag, reset, rebase, or branch deletion.
- Proceed under the authority established in Step 1; do not ask for the same confirmation twice. Push the head branch with an ordinary fast-forward push. No
--force,-f,--force-with-lease, or+refspecis permitted. - Query for an existing pull request on the head branch. Update its title and body when one exists; otherwise create one against the resolved base. Preserve command errors: a no-pull-request result permits creation, while authentication, permission, network, or validation errors block publication.
- Read the pull request back from the host. Confirm its URL, base, head, state, and published commit tip. Return the final report only when those values match the intended publication.
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.
- 5d ago First seen · 52 lines · 38 tokens per session scan A 82c5968b039c
review-and-ship is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,024 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 2026-09-06.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…