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 publish-branchgit 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/publish-branch)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/publish-branch"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/publish-branch/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/publish-branch"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/publish-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 63 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00060 | $0.01852 |
| Opus 5 | $0.00030 | $0.00926 |
| Sonnet 5 | $0.00012 | $0.00370 |
| Haiku 4.5 | $0.00006 | $0.00185 |
Grade A, and why
publish-branch 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit and push the current branch
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to commit and push to the branch currently checked out, including the default branch. |
| Authority | Remote: pushes local commits to origin/<current-branch>; requires explicit human invocation. Invoking on the checked-out branch (including main/master) is explicit authorization to push to that branch. Preview the push target and consequence before pushing. |
| Side effect | Creates local commits and pushes them to origin/<current-branch>. No branch creation, no branch switch, no force push, no PR. |
| Done | Current branch is committed and pushed, or detached/diverged/no-origin state is reported without unsafe recovery. |
Inputs
- Working-tree status (
git status) and diff against HEAD (git diff HEAD): required, gathered by the skill. - Current branch (
git branch --show-current): required, gathered by the skill; empty output means detached HEAD. - Recent commit history (
git log --oneline -10): required, gathered by the skill. - Push-target divergence: required, gathered by the skill with
git rev-list --left-right --count origin/$(git branch --show-current)...HEAD 2>/dev/null || echo 'NO_REMOTE_BRANCH'(left count = commits only on origin, right count = commits only on HEAD);NO_REMOTE_BRANCHmeans the branch has no counterpart on origin yet. - Configured remotes (
git remote): required, gathered by the skill. - A commit message supplied by the user: optional; when absent it is derived from the diff and the repo conventions.
Procedure
- Resolve branch state. Run
git branch --show-current.- Detached HEAD (empty output): there is no branch ref to push. Report that this skill pushes only the checked-out branch and stop. Never create or switch a branch.
- Any named branch: continue. The default branch is not special: invocation is consent to push from the current HEAD. Done when: a named branch is identified and recorded, or detached HEAD is detected and the stop is reported.
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 Changed · +20 tokens per session 5423e9be7916
- 4d ago First seen · 80 lines · 40 tokens per session scan A 3f69d86fd880
publish-branch is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 1,852 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 2026-09-06.
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…