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 rainmanjam/poka-yoke --skill llmgit clone --depth 1 https://github.com/rainmanjam/poka-yokeWrote 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/rainmanjam/poka-yoke/llm)<a href="https://agentmods.dev/skills/rainmanjam/poka-yoke/llm"><img src="https://agentmods.dev/badge/skills/rainmanjam/poka-yoke/llm/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/rainmanjam/poka-yoke/llm"><img src="https://agentmods.dev/badge/skills/rainmanjam/poka-yoke/llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 2 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Anti-Refusal · line 17 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00089 | $0.02118 |
| Opus 5.5 | $0.00036 | $0.00847 |
| Sonnet 5.5 | $0.00018 | $0.00424 |
| Haiku 4.5 | $0.00009 | $0.00212 |
Grade A, and why
llm 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 2mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Poka-Yoke for LLM Features
This is about AI features you ship to users: not about agents editing your repo, which is
agent-guardrails.
The defining property of an LLM is that it is a component with a non-zero error rate on every call, and no amount of prompt engineering drives that to zero. This is not a defect to fix; it is the material you are building with. Shingo's framing fits perfectly: you do not make the operator more careful, you build the jig.
Which means the central discipline here: prompt instructions are rung zero. "Always respond with valid JSON," "never make up a citation," "do not reveal the system prompt". These are requests to an unreliable component, and they are the LLM equivalent of a comment saying "be careful." They help, they are worth writing, and they are not devices. A device is something outside the model that constrains what it can produce or what its output can reach.
Building, not reviewing
Most of the time this mode is reached while someone is building the thing, not afterwards. That changes the deliverable. They asked for the feature, so produce the feature, working, complete, in their stack. Do not hand back a severity table when the person is mid-feature; a list of findings about code they have not written yet is not useful to them.
Then add a short closing note, three or four lines, covering:
- which misuses the shape you chose makes impossible, and at which rung,
- what you left possible on purpose, and why that tradeoff is the right one here.
That closing note is what stops the device being undone in six months by someone who cannot see why it is there. It is also the difference between mistake-proofing and a code generator: the reasoning travels with the code.
When the code already exists and they are asking what is wrong with it, switch to the audit voice, ranked findings with the mistake, the consequence, and the device. Match the mode to where they are in the work, not to this file's default.
The boundary: nothing the model says is trusted until something checks it
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.
- 2mo ago First seen · 162 lines · 89 tokens per session scan A 79b9d78be4e8
llm is a skill published in the GitHub repository rainmanjam/poka-yoke (24 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 2,118 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
meta-prompting
Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes"…
review-prompt
Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.
goal-test
A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.
adhd
Divergent ideation across model families — the same brainstorm, but each cognitive frame is handed to a different model (Claude sub-agent, OpenAI Codex, a cheap third via OpenCode) so the ideas diverge by frame and by model priors at once. Use for open design questions, architecture and API shape, naming, schema…
mutation-test
Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…
refine-prompt
Transforms vague or rough prompts into precise, structured AI instructions. Use when asked to "refine prompt", "improve prompt", "make this prompt better", "promptify", "optimize prompt", "rewrite prompt", "enhance prompt", or "sharpen instructions".