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/outlinedriven/odin-claude-plugin/commit-economynpx skills add OutlineDriven/odin-claude-plugin --skill commit-economygit 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/commit-economy)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/commit-economy"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/commit-economy.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.01090 |
| Opus 5 | $0.00031 | $0.00545 |
| Sonnet 5 | $0.00012 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
commit-economy 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.
This is a copy
100% identical to commit-economy — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit economy
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to clean up a finished commit's message, or a commit message needs handoff-ready form. |
| Authority | Rewrite only VCS-tracked commit messages. Show the exact commit set before mutation. Use the original refs and reflog as recovery. Never create or suggest a new commit. |
| Side effect | Rewrites commit messages only; the tree stays byte-identical; each rewritten commit is re-signed with its dates preserved by position. Local history only. |
| Done | git diff old..new is empty; each rewritten commit is signed with the intended dates; git log alone carries the handoff with the diff hidden. |
Inputs
- The target commit or range:
HEADor a short unpushed range (HEAD~N..HEAD). Optional; default isHEAD. - The intended message text for each target commit. Must be supplied by the user or derived from the existing message; never invented.
- Confirmation when any target commit is already pushed to a shared remote. Required before proceeding; otherwise stop.
Procedure
- Determine the exact target set:
HEAD, orHEAD~N..HEADfor a short unpushed range. List the commits withgit log --format='%H %an <%ae> %ad %cn <%ce> %cd' <range>so the set and per-position author/committer dates are visible. Done when: the exact commit set is listed with per-position dates. - Confirm that none of the target commits are pushed to a shared remote (
git branch -r --contains <sha>). If any is pushed, stop and require explicit user confirmation before continuing. Pushed history is otherwise untouched. Done when: all targets are confirmed unpushed or explicit confirmation is received for pushed commits. - Record each target commit's original tree SHA (
git rev-parse <sha>^{tree}) and original author and committer dates, keyed by position in the range. Re-signing must preserve these dates by position. Done when: every target's tree SHA and dates are recorded by position. - Never create or suggest a new commit. Only rewrite the message of existing commits in the target set. Done when: the no-new-commit constraint is confirmed before mutation.
- Rewrite each target commit's message to handoff-ready form. When the diff is hidden, the message must let
git logalone carry the handoff by stating what changed and why without relying on the diff. Usegit rebasewithGIT_SEQUENCE_EDITORandgit commit --amend/--reedit-message, orgit filter-repo --message-callback, scoped to the exact range. Done when: every target commit's message is rewritten to handoff-ready form. - Re-sign each rewritten commit while preserving its original author and committer dates by position. Set
GIT_AUTHOR_DATEandGIT_COMMITTER_DATEto the recorded per-position values during each amend; do not let them slip to now. Done when: every rewritten commit is re-signed with its original dates by position. - Verify the done predicate: run
git diff <old>..<new>and confirm it is empty (tree byte-identical); confirm each rewritten commit's author and committer dates match the recorded per-position values; confirmgit logfor the range carries the handoff withgit show/diff hidden. Done when: the diff is empty, dates match by position, and the log carries the handoff.
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.
- 2d ago First seen · 42 lines · 62 tokens per session scan A 02da58476502
commit-economy is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,090 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to commit-economy, differing in 0 lines, and is treated as a copy.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…