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 tomzx/agents --skill review-decisiongit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/review-decision)<a href="https://agentmods.dev/skills/tomzx/agents/review-decision"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-decision/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/tomzx/agents/review-decision"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-decision.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 | $0.00020 | $0.00774 |
| Opus 5 | $0.00010 | $0.00387 |
| Sonnet 5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
review-decision 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 6d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Decision
Audits a decision record and reports findings across four categories: clarity, completeness, reasoning quality, and consequence coverage.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. .sdlc/knowledge/decisions/N-<slug>.md, or a decision document provided in context or as a file path
Steps
- Read the decision document.
- Evaluate it against the checklist below.
- Report findings by category. Omit categories with no findings.
- After the review, update
statusin frontmatter to the appropriate value:Accepted,Deprecated, orSuperseded by [N].
Review Checklist
Clarity
- Is the decision stated as a specific, unambiguous choice (not a direction or intent)?
- Is the title a noun phrase that names the decision, not just the topic?
- Is the status field present and accurate (Proposed / Accepted / Deprecated / Superseded)?
Completeness
- Is the context section present and does it explain what problem or question prompted the decision?
- Are at least two options described, including the one chosen?
- Does each option have at least one pro and one con?
- Are trade-offs (gained vs. sacrificed) explicitly stated?
Reasoning Quality
- Does the reasoning connect the context and constraints to the chosen option?
- Are pros/cons specific to this situation rather than generic statements?
- Is it clear why the chosen option was preferred over the alternatives?
- Are any options dismissed without justification?
Consequence Coverage
- Are the practical effects on the codebase or process described?
- Are follow-up decisions or deferred work identified?
- Are risks introduced by this decision acknowledged?
Output Format
## Clarity
<Findings or "No issues found.">
## Completeness
<Findings or "No issues found.">
## Reasoning Quality
<Findings or "No issues found.">
## Consequence Coverage
<Findings or "No issues found.">
Outcome
If $OUTCOME_YAML is set, emit your verdict there per skills/sdlc/references/shared.md:
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.
- 6d ago First seen · 100 lines · 20 tokens per session scan A bd1bcd5ba592
review-decision is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 774 once invoked, about $0.0001 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 2026-09-03.
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…