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 SerenecoTech/agent-skills --skill review-designgit clone --depth 1 https://github.com/SerenecoTech/agent-skillsWrote 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/serenecotech/agent-skills/review-design)<a href="https://agentmods.dev/skills/serenecotech/agent-skills/review-design"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/review-design/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/serenecotech/agent-skills/review-design"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/review-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00118 | $0.00538 |
| Opus 5 | $0.00059 | $0.00269 |
| Sonnet 5 | $0.00024 | $0.00108 |
| Haiku 4.5 | $0.00012 | $0.00054 |
Grade A, and why
review-design 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 10d 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.
What it actually says
Adversarial design and specification review
A front door. All mechanics live in the engine — read
../../engine/ENGINE.md and follow it.
Resolve the target
The user may give file paths, inline prose describing the idea, or both. Note the paths; you will point codex at them by absolute path, never by pasting their contents.
If nothing was provided: No concept provided. Pass a description, file paths, or both.
If the concept is inline only, with no file to cite, say so in the output — findings cannot carry verbatim citations against prose that exists only in the prompt, so the proof-of-work citation check does not apply and the review is weaker for it. Prefer writing the concept to a file first.
Then
- Load the engine, then both
rubric-architecture.mdandrubric-document.mdunless the artefact is plainly only one. Most specs are both, and loading one because of which door fired gives the same artefact a different review. - Follow the engine: loop shape, scope gate, rounds, convergence, output.
- Default to the verdict loop. Enter the fix loop only on an explicit grant to edit.
Watch for
- Right measurement, wrong quantity. Both sides agreeing on a number that does not decide anything. Ask what observation would change the decision, then measure that.
- Agreement by exhaustion. Later rounds going quiet because the brief narrowed. The candidate-final round takes the whole artefact for exactly this reason.
- A design's account of current behaviour is the most commonly wrong part of it. Read the behaviour, do not trust the description.
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.
- 10d ago First seen · 47 lines · 118 tokens per session scan A 85906429952e
review-design is a skill published in the GitHub repository SerenecoTech/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 118 tokens to every session and 538 once invoked, about $0.0006 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 2026-08-31.
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…