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 release-promotiongit 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/release-promotion)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/release-promotion"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/release-promotion/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/release-promotion"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/release-promotion.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 | $0.00056 | $0.01168 |
| Opus 5 | $0.00028 | $0.00584 |
| Sonnet 5 | $0.00011 | $0.00234 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
release-promotion 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promotion copy
Contract
| Field | Bound contract |
|---|---|
| Trigger | /release-promotion [what shipped and/or channels] |
| Authority | Read-only; drafts copy only. It never posts, publishes, schedules, commits, or opens PRs. |
| Side effect | None. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Done | Every drafted channel is presented as a labeled copy-pasteable block and the user is offered a revision. |
Refusals
- Posting, publishing, scheduling, committing, or opening PRs: rejected. Drafts are the user's to ship.
- Fabricating value claims: rejected. If what shipped cannot be determined, ask one short question rather than guessing.
- Reusing one draft verbatim across channels: rejected. Each channel gets its own shape.
Inputs
The free-form argument is the source of truth for what shipped and which channels to draft. Both are optional: when omitted, derive what shipped from repository context and default channels to an X post (or short thread) plus a one-line changelog or release blurb. If the user named channels (LinkedIn, email, a blog intro, a demo script), draft those instead of or in addition to the defaults.
Procedure
- Determine what shipped. Prefer the argument when supplied. Otherwise derive it from available context:
gh pr view --json title,body,urlfor the merged or active PR;git diff main...HEAD --statto skim notable changes; the top or[Unreleased]entry indocs/changelog.md,CHANGELOG.md, or similar;git log --oneline -15for the arc of the change. Done when: a confident value summary is produced or one short question is asked. - Write a 1-3 sentence summary of the user-facing value: what a user can now do that they could not before, and why they would care. State outcome, not implementation. Done when: the value summary is written.
- Pick channels. Default to an X post or short thread plus a one-line changelog or release blurb. If the user named channels, draft those instead of or in addition to the defaults. Scale to the change: a small fix warrants one or two short drafts; a flagship feature warrants a cross-channel set. Done when: the channel set is selected.
- Draft each channel following shared rules: lead with the user-facing outcome, not how it was built; one idea per piece; cut windup, hedges, and throat-clearing; plain active language; strip AI tells ("thrilled/excited to announce", "game-changer", "in today's fast-paced world", "unlock/leverage/filler-verbs", em-dash padding); read it back as if saying it to one user and rewrite if a person would not say it. Done when: each channel has a first draft.
- For distributed channels, make the first line the hook that earns the next line, since feeds truncate; match each channel's native shape and length; never reuse one draft verbatim across channels; include one clear CTA where the channel supports it; use 0-2 hashtags only where the channel expects them. Done when: each distributed channel draft has a hook, native shape, and CTA.
- Apply per-channel shape: X: value in the first line, ~1-3 tight lines, thread only when there is more than one beat worth its own line; changelog or release blurb: one declarative line naming the new capability, plain not promotional; LinkedIn: a short paragraph with a human angle then the what, warmer than X; email: benefit-stating subject plus 2-4 sentence body plus one CTA; blog intro: one opening paragraph framing the problem and the new capability, leaving the deep-dive to the author; demo script: 3-6 spoken beats (hook, problem, action, payoff). Produce one strong draft per channel by default; produce more only when asked, capped at ~3. Done when: each channel draft matches its per-channel shape.
- Present every draft as a clean, copy-pasteable block labeled by channel, e.g.
### X postfollowed by the copy. Offer to revise (tone, length, angle, more variations, another channel). Remind the user the drafts are theirs to ship; do not post, publish, schedule, commit, or open a PR. Done when: every draft is presented with a label and a revision offer.
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 · 47 lines · 56 tokens per session scan A ed4331367611
release-promotion is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,168 once invoked, about $0.0003 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 2026-09-04.
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…