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 diamond-taskgit 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/diamond-task)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/diamond-task"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/diamond-task/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/diamond-task"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/diamond-task.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 | $0.00059 | $0.01304 |
| Opus 5.5 | $0.00024 | $0.00522 |
| Sonnet 5.5 | $0.00012 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
diamond-task 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
100% identical to diamond-task — 4 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diamond task
Contract
| Field | Bound contract |
|---|---|
| Trigger | Use when one issue or pull request is too large or too entangled for one worker and its complete writable surface can be partitioned into disjoint write sets. |
| Authority | Reversibly write only the named local run artifacts and declared target write sets. Preserve a pre-run checkpoint and restore it on terminal failure. This is the sole production task-DAG generator. |
| Side effect | Run isolated workers and apply their returned diffs by mechanical union within their declared write sets; the composer authors no content and changes nothing outside those sets. |
| Done | Produce one result that reproduces every worker diff byte-for-byte within disjoint declared write sets and has approval from a fresh isolated reviewer who was neither a worker nor the composer, or stop with no partial composition and identify the falsified worker node or split. |
Inputs
Required inputs are one issue or pull request with its acceptance criteria, the local target workspace, the checks each worker and the composed result must satisfy, and named local locations for the checkpoint, isolated composition, and run report. Supply any fixed ordering constraints between units of work; otherwise the partition determines independent worker nodes. The target's current bytes and metadata are the composition base. The production task DAG is derived from the supplied units of work and their declared ordering constraints only.
Procedure
-
Capture the exact target base in the named checkpoint. Enumerate every target byte the task may create, replace, or delete, including integration edits, formatting changes, and generated output that the final result requires. Done when: the checkpoint captures the exact base and the complete writable surface is enumerated.
-
Design the production task DAG by partitioning that complete writable surface into worker nodes with pairwise-disjoint write sets. Define each set by canonical target paths and, when a path is shared, non-overlapping byte regions or insertion boundaries. Give each node its task, allowed write set, required checks, required proof, and only the inputs it needs. Every content byte the composer might otherwise need to author must belong to a worker node. Stop before worker execution if coverage is incomplete, any sets overlap, or isolation cannot be provided. Done when: the DAG partitions the surface into disjoint covering write sets with every content byte owned by a node, or the skill stops on incomplete coverage, overlap, or missing isolation.
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 · 44 lines · 59 tokens per session scan A 3a5aec7b073c
diamond-task is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (37 stars, last pushed 22d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,304 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to diamond-task, differing in 4 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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…