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 automate-megit 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/automate-me)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/automate-me"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/automate-me/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/automate-me"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/automate-me.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.00937 |
| Opus 5 | $0.00029 | $0.00468 |
| Sonnet 5 | $0.00012 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
automate-me 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 6d 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 automate-me — 6 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automate me
Contract
| Field | Bound contract |
|---|---|
| Trigger | Create or refresh a personal mode skill. |
| Authority | Human-only. Require explicit human invocation; preview the target file, skill content, and PR consequence before any write, push, or remote publish. |
| Side effect | Creates or edits one personal mode skill file in a local working copy on a new branch, commits it, pushes the branch, and opens a reviewable PR. No files beyond that skill file and no remote state beyond that branch and PR are touched; no credentials are read or written. |
| Done | Evidence-backed personal mode skill in a reviewable PR. |
Inputs
- A personal workflow to encode, supplied either as a direct description by the human or as a pointer to recent session or conversation history to mine for a repeated manual task pattern. At least one of these must be present.
- Target skill slug and file path. Optional; derive a slug from the workflow if the human does not supply one, and confirm it before writing.
- Repository and base branch to open the PR against. Must be supplied or determinable from the current working copy; if neither, stop and ask.
Procedure
- Require explicit human invocation. Confirm the human intends to author or refresh a personal mode skill and open a remote PR for it; do not proceed on inferred intent. Done when: the human confirms intent to author a personal skill and open a PR.
- Identify the recurring personal workflow. Use a description supplied by the human. Otherwise, mine recent session or conversation history for a task the human performs manually more than once. Name the repeated pattern and the sessions where it appears as evidence. Done when: the recurring workflow is named with supporting session evidence.
- If no recurring workflow can be supported by the history or description, stop and report that there is no candidate. Do not invent a workflow or fabricate history evidence. Done when: the absence of a candidate is reported or a candidate is confirmed.
- Draft the personal mode skill as a self-contained skill file with a name, trigger predicate, short procedure, and required inputs. The skill must not depend on another skill, module, or external rule file. Done when: the skill file is drafted as self-contained with all required sections.
- Show the human the target file path, full skill content, branch name, and consequence of opening a PR. Wait for explicit approval before any mutation. Done when: the human approves or declines the preview.
- On approval, create a new branch in the local working copy and create or edit the skill file at its target path. Write only that one file. Done when: the skill file is written on a new branch and no other file is touched.
- Commit the change with a message naming the personal workflow encoded. Done when: the commit is created with the workflow-naming message.
- Push the branch and open a reviewable PR whose description states the workflow encoded, the history evidence used, and the skill file path. Done when: the branch is pushed and the PR is opened with the required description.
- Capture the PR URL as the success evidence. Done when: the PR URL is captured.
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.
- 6d ago First seen · 45 lines · 58 tokens per session scan A 653934eebc84
automate-me is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 937 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 automate-me, differing in 6 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…
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…