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 grill-with-docsgit 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/grill-with-docs)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/grill-with-docs"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/grill-with-docs/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/grill-with-docs"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/grill-with-docs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00569 |
| Opus 5.5 | $0.00014 | $0.00228 |
| Sonnet 5.5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
grill-with-docs 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill with docs
Contract
| Field | Bound contract |
|---|---|
| Trigger | A repository decision needs an interview plus durable terminology and decision records. |
| Authority | Reversible local: writes only CONTEXT.md and ADR files in the working repository; rollback is version control or undo. No remote mutation. |
| Side effect | CONTEXT and ADR updates during the interview. |
| Done | Frontier empty and no resolved term left unwritten. |
Inputs
A repository working tree containing a decision to make. Optional: an existing CONTEXT.md and an ADR directory; both are created when absent.
Procedure
- Read the code domain model that the decision touches: entry points, types, and the modules on that surface. Bound the interview scope to this surface before any write. Done when: the entry points, types, and modules on the decision surface are read, and the interview scope is bounded to that surface with no write made.
- Build the frontier: enumerate every unresolved term and open question the decision depends on. Done when: every unresolved term and open question the decision depends on is enumerated, and the frontier list is non-empty or the decision is confirmed to need no interview.
- For each frontier item, ask one question. Consult the code, then resolve the term or decision against evidence found in the repository. Done when: each frontier item has a question asked, the code is consulted, and the term or decision is resolved against evidence found in the repository or marked unresolved.
- As each item resolves, write the resolved term into CONTEXT.md and the resolved decision into a numbered ADR file. Done when: each resolved term is written into CONTEXT.md and each resolved decision is written into a numbered ADR file, and both files are confirmed on disk.
- Repeat until the frontier is empty. Done when: the frontier list is empty, every item is resolved and written or marked open, and no unresolved item remains unrecorded.
Failure and recovery
- Unresolved term: leave it on the frontier, mark the corresponding CONTEXT or ADR entry as open, and stop rather than write an ungrounded definition.
- Partial result: committed CONTEXT and ADR entries stand; the remaining frontier is reported as open.
- Rollback: revert or delete the CONTEXT.md and ADR files written this session. No other artifacts are touched.
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 Changed · +1 lines · -20 tokens per session 648668514de5
- 1mo ago First seen · 36 lines · 55 tokens per session scan A 1525f8780eb1
grill-with-docs is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 25d ago), licensed Apache-2.0. It adds 35 tokens to every session and 569 once invoked, about $0.0001 per session on Opus 5.5. 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
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…