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 agentmods add skills/flutter/agent-plugins/api-reviewnpx skills add flutter/agent-plugins --skill api-reviewgit clone --depth 1 https://github.com/flutter/agent-pluginsWhat 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 | $0.00034 | $0.00450 |
| Opus 5 | $0.00017 | $0.00225 |
| Sonnet 5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
api-review 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- api-review — 91% identical, 2 lines differ
What it actually says
API review skill
This skill reviews code against the canonical API Design guidelines.
Instructions
- Load Guidelines: Read the API design guidelines from references/canonical_api_design.md to ensure they are fully available in the context.
- Identify Target: Identify the code to review.
- If the user specified files (e.g., "review main.dart"), use those.
- If the user has an open file in their context, assume that is the target.
- If neither, ask the user to specify the target files.
- Analyze: For each target file, perform a deep analysis against the "Foundations of Canonical API Design Principles" (loaded in step 1), specifically looking for:
- Contract-First: Is the interface clear and decoupled from implementation?
- KISS/YAGNI: Are there unnecessary parameters or over-generalized features?
- Ergonomics: Are names intent-revealing? Do they follow the Principle of Least Astonishment?
- CQS: Are commands and queries separated?
- Safety: Are types used strictly (Enums vs Strings)? Is validation visible?
- Explicit Configuration: Are dependencies explicitly injected rather than implicitly resolved via global state, registries, or environment variables?
- Report: Generate a structured report:
- Score: Give a letter grade (A-F) based on alignment.
- Critical Issues: Violations that must be fixed (e.g., severe strictness or safety issues).
- Suggestions: Ergonomic improvements (renaming, rearranging).
- Code Examples: Provide
beforevsaftercode blocks for the suggested improvements. - Save the report as a markdown artifact in the conversation artifacts directory (e.g.,
<appDataDir>/brain/<conversation-id>/api_review_results.md).
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.
- yesterday First seen · 30 lines · 34 tokens per session scan A 75dfef71701f
api-review is a skill published in the GitHub repository flutter/agent-plugins (2,895 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 34 tokens to every session and 450 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…