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 git-workflow-and-versioninggit 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/git-workflow-and-versioning)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/git-workflow-and-versioning"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/git-workflow-and-versioning.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.01047 |
| Opus 5 | $0.00021 | $0.00524 |
| Sonnet 5 | $0.00008 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
git-workflow-and-versioning 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git workflow and versioning
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks for release, version bump, changelog, or branch workflow beyond a single commit. |
| Authority | Human-gated: previews the exact target and consequence before any push, protected-branch action, or force-push, with explicit consent required for protected branches and force-pushes; otherwise reversible local: writes only local commits, tags, and changelog edits; rollback is version control. No remote mutation without the gate. |
| Side effect | Git commits, tags, and changelog edits; protected branches and force-pushes only with explicit consent. |
| Done | History expresses logical change-sets, tags and changelog match shipped contract changes, and no unauthorized protected-branch action occurred. |
Inputs
Required: the change-set to release or version (working-tree state, staged changes, or committed history since the last tag); the target version bump type or an explicit version string; the branch to operate on.
Optional: changelog path, remote name, tag message, prerelease suffix.
Procedure
- Confirm the request names a release, version bump, changelog update, or branch workflow beyond a single commit. If it is a single commit, stop and defer to the caller. Done when: the request names a release/version/changelog/branch-workflow beyond one commit, or the run deferred a single-commit request.
- Inspect the working tree and recent history with
git status,git logsince the last tag, and the current branch. Identify the logical change-sets to express. Done when: working tree, history since last tag, and current branch inspected and change-sets identified. - Group changes into atomic commits so each commit is one logical change-set. Stage and commit each group with a message that states the change, not the diff. Done when: changes grouped into atomic commits, each one logical change-set with a change-stating message.
- Derive the version bump from the change-sets (major for breaking contract changes, minor for additive, patch for fixes), or use the explicit version the user supplied. Done when: the version bump is derived from change-sets or the user-supplied version is adopted.
- Update the changelog so each new entry matches a shipped contract change; date and version the new section. Done when: the changelog''s new entries each match a shipped contract change, dated and versioned.
- Preview the exact commits, tag, and changelog diff to the user before any tag, push, or protected-branch action. Done when: the commits, tag, and changelog diff are previewed to the user before any tag, push, or protected-branch action.
- Create the version tag only after explicit human confirmation. Use an annotated tag carrying the version message. Done when: an annotated version tag is created only after explicit human confirmation.
- For any push, protected-branch target, or force-push, state the target and consequence and require explicit consent before executing. Never force-push or push to a protected branch without it. Done when: every push, protected-branch target, or force-push states target and consequence and has explicit consent before executing.
- After mutation, verify
git log,git tag, and the changelog reflect the intended state and confirm no unauthorized protected-branch action occurred. Done when:git log,git tag, and the changelog reflect the intended state with no unauthorized protected-branch action.
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 · 46 lines · 42 tokens per session scan A fee022888408
git-workflow-and-versioning is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,047 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…