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 instruction-understanding-gategit 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/instruction-understanding-gate)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/instruction-understanding-gate"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/instruction-understanding-gate/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/instruction-understanding-gate"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/instruction-understanding-gate.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 | $0.00043 | $0.00914 |
| Opus 5 | $0.00022 | $0.00457 |
| Sonnet 5 | $0.00009 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
instruction-understanding-gate 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruction understanding gate
Verify understanding before acting.
Contract
| Field | Bound contract |
|---|---|
| Trigger | Long/bundled/high-stakes/hard-to-undo instruction, or ambiguous scope/referents (this, that, it, whatever is cleaner) |
| Authority | Reversible local: writes at most one durable understood-as log line for substantial work, after the gate decision; rollback is revert to pre-check state. No remote mutation. |
| Side effect | None before the gate passes; at most one clarifying question and one durable understood-as log line for substantial work |
| Done | Restatement is a paraphrase; every surfaced fork is genuinely unresolved by available context; no substantial work starts otherwise |
Inputs
The user's instruction and all readable context: the current message, session history, project memory files, filesystem, and established project conventions. The model obtains these inputs; the user does not need to provide an artifact.
Procedure
-
Check the read signal. Recognize when the instruction is long, multi-part, ambiguous in scope or referents, deliberately flexible, or high-stakes enough that a wrong read costs real work. If none of these signals are present, stop. Done when: the matched signals are named, or none is and the gate stops here.
-
Restate the instruction. Paraphrase the instruction in the agent's own words. Do not copy the user's wording and treat that as understanding. Done when: the instruction is paraphrased in the agent's own words, not copied from the user.
-
Cross-check against context. Compare the restatement against all available context: the current message, session history, project memory, files on disk, and established conventions. Look for contradictions, missing antecedents, or two plausible readings that context cannot choose between. Done when: the restatement is cross-checked against all available context and any contradictions, missing antecedents, or unresolvable forks are identified.
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 Changed · -24 tokens per session 09b4bbf36feb
- 5d ago First seen · 55 lines · 67 tokens per session scan A 88ce8c2d99a0
instruction-understanding-gate is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 914 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…
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…