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 decision-rationale-gapsgit 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/decision-rationale-gaps)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/decision-rationale-gaps"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/decision-rationale-gaps/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/decision-rationale-gaps"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/decision-rationale-gaps.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 | $0.00033 | $0.01095 |
| Opus 5 | $0.00016 | $0.00548 |
| Sonnet 5 | $0.00007 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
decision-rationale-gaps 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 3d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Press decision
Contract
| Field | Bound contract |
|---|---|
| Trigger | Right after a decision was made, especially one laid out without argument |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | None (advisory); flags the decision for re-review on an unexplained gap |
| Done | Every closed gap traces to the user's own explanation; open gaps named specifically and carried forward as flags; rationale never supplied by the skill |
Inputs
- Decision text: The decision statement to press. Required. Must be the decision that was made, not the reasoning behind it.
- Context (optional): Any surrounding context about what options were considered and which was picked.
Procedure
- Restate neutrally: State the decision without justification. Do not supply its reasoning or let the user borrow reasoning that was never given. Done when: the decision is restated without justification.
- Isolate the critic: Hand only the decision, without any reasoning, to a fresh session that did not watch the decision get made. Do not pass the optional Context; it carries the reasoning the critic must not see. Instruct it to identify gaps: what a skeptical outsider would challenge, what is assumed but unstated, and what must be true for the choice to hold. Done when: the critic session receives only the decision and returns gap candidates.
- Return one gap: Keep the critic's full response as the candidate pool for the whole press. Extract the single sharpest unresolved gap that no earlier round has extracted. Never batch gaps into a checklist. Each closed gap returns here for the next candidate. When no unextracted candidate remains, the gap loop ends at step 7. Done when: one gap is extracted, or the critic response is empty and the gap is named as unresolved-critic-response, or the pool is exhausted and the loop ends.
- Press the user: Present the current question, the extracted gap or its narrowed form, and ask the user to explain it in their own words. The skill never supplies the rationale. Done when: the current question is presented to the user for their explanation.
- Judge the answer:
- If the answer actually resolves the gap: close it and return to step 3 to extract the next gap from the candidate pool.
- If it restates the question, deflects, or leans on authority ("the agent suggested it"): do not accept it.
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.
- 3d ago First seen · 47 lines · 33 tokens per session scan A a50a765f3f37
decision-rationale-gaps is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,095 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 2026-09-06.
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…