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 record-design-decisionsgit 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/record-design-decisions)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/record-design-decisions"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/record-design-decisions/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/record-design-decisions"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/record-design-decisions.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 | $0.00050 | $0.00869 |
| Opus 5 | $0.00025 | $0.00434 |
| Sonnet 5 | $0.00010 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
record-design-decisions 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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record design decisions
Contract
| Field | Bound contract |
|---|---|
| Trigger | Codebase terminology or a durable technical decision changes. |
| Authority | Reversible local writes only; no remote, credential, paid, or deployed mutation. |
| Side effect | Immediate glossary (CONTEXT) and ADR writes to the repository. |
| Done | Every resolved term and qualifying decision is recorded. |
Refusals
- No recordable content: if no terminology change or qualifying decision is present, do not write anything. Stop.
- Invalid target: if the target path is outside the repository root, stop rather than write. A path outside the repository root is a trust violation and halts the whole skill.
- Unavailable ADR directory: if the ADR directory does not exist and cannot be created, do not halt the whole skill. Record the terminology change if present, skip the ADR, and return
non-converged(see Failure and recovery). - Untrusted input in records: rejected. Validate each write at its trust boundary.
Inputs
- Changed term or decision (required): the term or decision that triggered invocation.
- Resolution context (required): what was agreed, chosen, or ruled out.
- Rejected alternatives (optional, but required for a qualifying decision): alternatives considered and why they were rejected.
- ADR triple (required for a qualifying decision): three affirmative answers confirming that the decision is hard to reverse, surprising without context, and carries a real trade-off.
Procedure
- Identify the changed term or decision from the invocation context. Done when: the change is named.
- Determine whether the change is a terminology resolution, an ADR-qualifying decision, or both. Done when: the change type is classified.
- For terminology changes: write the resolved term to
CONTEXT.mdusingassets/CONTEXT-FORMAT.md. Done when: the CONTEXT entry is written. - For qualifying decisions: write an ADR to
docs/decisions/usingassets/ADR-FORMAT.md. Done when: the ADR file is written. - Validate each write at its trust boundary: check the target file or directory is within the repository root and that the content does not contain untrusted input. Done when: every write passes validation.
- Write the records before the session continues. Done when: all records are persisted.
- Stop if no term resolves and no decision qualifies. Do not invent content. Done when: the procedure has stopped with
blocked:no-recordable-contentor all records are written.
What ships with it
3 files 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.
- 5d ago First seen · 51 lines · 50 tokens per session scan A a5503bd2dc0c
record-design-decisions is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 869 once invoked, about $0.0003 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…
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…