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 close-donegit 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/close-done)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/close-done"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/close-done/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/close-done"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/close-done.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 | $0.00037 | $0.00810 |
| Opus 5.5 | $0.00015 | $0.00324 |
| Sonnet 5.5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
close-done 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 1mo 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
91% identical to close-done — 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close done
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to batch-close resolved or outdated tracker items. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. The agent fetches, classifies, and presents the batch; the user performs every remote closure. |
| Side effect | A prepared batch list presented to the user. No tracker item is mutated by this skill. |
| Done | A prepared batch list is presented to the user for manual closure, with each item classified as resolved or outdated and backed by evidence. |
Inputs
- The candidate tracker items, supplied as numbers, URLs, a filter, or a query the agent can resolve against the configured tracker.
- Optional: a reason or resolution note the user will attach when closing.
- Tracker host and credentials are those already configured in the environment; the agent does not create or modify credentials.
Classification criteria
An item qualifies for the batch only when it meets one of these evidence-backed criteria:
- Resolved: the item's tracker state is closed-done or merged, or the item references a merged pull request, commit, or deployment that addresses it. Evidence: the tracker state field, a linked PR/commit with a merged status, or a resolution comment from the assignee.
- Outdated: the item has had no activity for a period the user defines (default 90 days), and no open PR or branch references it. Evidence: the last-activity timestamp and the absence of linked open work.
Items that do not meet either criterion are excluded. List each excluded item with the reason it failed the criteria.
Procedure
- Resolve the supplied references or filter against the tracker read-only and fetch each item's number, title, current state, last activity timestamp, and linked PRs or branches. Done when: every supplied item is resolved with its metadata or the failing item is named.
- Classify each item as resolved or outdated using the criteria above. Drop items that are neither and list them as excluded with the reason. Done when: every item has a classification with its evidence or an exclusion reason.
- Prepare the final batch list: every item proposed for close with its number, title, current state, classification (resolved or outdated), and the evidence supporting it. Done when: the full batch is listed and no mutation has occurred.
- Present the batch to the user for manual closure. State that the agent will not close any item and that the user must perform the closure on the tracker. Include the optional resolution note for the user to attach. Done when: the batch is presented and the user has the closure instructions.
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.
- 1mo ago First seen · 51 lines · 37 tokens per session scan A bd5cb120b531
close-done is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (38 stars, last pushed 24d ago), licensed Apache-2.0. It adds 37 tokens to every session and 810 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to close-done, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…