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 necessary-workgit 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/necessary-work)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/necessary-work"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/necessary-work.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 | $0.00047 | $0.00781 |
| Opus 5 | $0.00023 | $0.00391 |
| Sonnet 5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
necessary-work 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Necessary work
Contract
| Field | Bound contract |
|---|---|
| Trigger | Work is about to grow past the ask, the task may already be done, or the user requests the minimum, only what is needed, or a stop once it works. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Reads and assesses request, environment, policy, and evidence only. |
| Side effect | Narrow the scope of work by classification only; produce no operational side effect. |
| Done | The contract is written before work, every admitted action fails the delete test, and classification stops once the minimum proof is identified. |
Inputs
Supply the request and the available evidence of its current state. Include any binding environmental limits or authoritative policies that constrain the outcome. Existing measurements are optional; do not create measurements unless the delete test establishes that they are necessary. If the request is ambiguous and the available inputs cannot resolve it, use the smallest interpretation consistent with the stated intent and record that interpretation.
Procedure
- Write the contract before admitting work: state the requested outcome and the minimum evidence that would prove it. Done when: the outcome and its proof requirement are stated in writing.
- Enumerate only candidate actions that could close a stated outcome or proof gap. Treat no action as automatically necessary because it is useful, conventional, safer, cleaner, or more thorough. Done when: every plausible candidate is listed and none is admitted by default.
- For each candidate
c, apply the delete test: if deletingcwould leave the contract unmet or unproven, admit only the smallest reliable form ofc; otherwise reject it. Done when: every candidate has an admit-or-reject decision with its delete-test result. - Admit a limit, threshold, retry, budget, abstraction, artifact, check, process, or follow-up only when its necessity comes from the request, the environment, authoritative policy, or measured evidence. Done when: every admitted action has a named necessity source.
- Classify the admitted and rejected candidates without executing them or changing any state. Do not widen scope or invent evidence when an input is missing. Done when: the classification is complete and no state has changed.
- Stop as soon as the admitted actions and minimum proof are sufficient for the contract. Do not add speculative follow-up work. Done when: the minimum sufficient set is identified and no further candidate is considered.
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 Changed · -12 tokens per session c16b84c8708e
- 3d ago First seen · 42 lines · 59 tokens per session scan A 424d7c81deed
necessary-work is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 781 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 2026-09-04.
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…