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/strvcom/flutter-template/pr-reviewnpx skills add strvcom/flutter-template --skill pr-reviewgit clone --depth 1 https://github.com/strvcom/flutter-templateWhat 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 | $0.00065 | $0.01870 |
| Opus 5 | $0.00032 | $0.00935 |
| Sonnet 5 | $0.00013 | $0.00374 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
pr-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 2d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter Template PR Review
Use this skill when reviewing a pull request, branch diff, or a set of code changes in this repository.
Review Goal
Prioritize finding:
- bugs
- regressions
- broken assumptions
- architecture drift
- missing tests
- upgrade or release risks
Do not treat the review as a style-polish exercise unless the user asks for that explicitly.
Read First
AGENTS.mddocs/PROJECT_OVERVIEW.mddocs/PROJECT_GUIDELINES.md- any changed files
Determine Review Scope
Parse the user's request and choose the smallest matching diff scope.
| User asks for | Review scope |
|---|---|
| default, branch review, PR review | git diff <default_branch>...HEAD |
| uncommitted changes | git diff plus git diff --cached |
| a specific commit | git show <commit> |
| last N commits | git diff HEAD~N...HEAD |
| branch X vs Y | git diff X...Y |
| explicit commit range | git diff <range> |
Detect the default branch with:
git symbolic-ref refs/remotes/origin/HEAD | sed 's|refs/remotes/origin/||'
If that fails, try main, then master.
Gather:
git diff --name-status <range>
git diff --stat <range>
git diff --unified=5 <range>
For uncommitted reviews, gather both unstaged and staged diffs. If there are no changes, say so and stop. If there are more than 50 changed files, warn that it is a large review and ask whether to proceed or narrow the scope.
Classify Changed Files
Classify every non-deleted changed file before reviewing so the right standards are applied. A file can belong to multiple categories.
| Category | File patterns | Review focus |
|---|---|---|
| Feature UI | lib/features/**/**_page.dart, lib/features/**/**_page_content.dart |
page thinness, shared widgets, localization, theme extensions, user-facing states |
| Feature state | lib/features/**/**_state.dart, lib/features/**/**_event.dart |
Riverpod orchestration, async gaps, freezed unions, one-off events |
| Navigation | lib/app/navigation/**, changed @RoutePage() widgets |
AutoRoute registration, generated route expectations, deep-link or shell behavior |
| Data and entities | lib/common/data/dto/**, lib/common/data/entity/**, lib/common/data/enum/** |
DTO/entity separation, JSON/freezed annotations, resilient mapping |
| Use cases and providers | lib/common/usecase/**, lib/common/provider/**, lib/core/** |
IO boundaries, provider lifetimes, startup assumptions, service wiring |
| Theme and shared UI | lib/app/theme/**, lib/common/component/**, lib/common/composition/** |
reuse, accessibility, edge-to-edge/system bar behavior, visual consistency |
| Localization and assets | assets/localization/**, pubspec.yaml, asset inputs |
generated accessors, context.locale, make gen expectations |
| Tests | test/**, integration_test/** |
coverage quality, realistic assertions, Patrol vs widget-test boundaries |
| Platform files | android/**, ios/**, web/**, macos/**, linux/**, windows/** |
flavor config, Firebase, signing, native build risks |
| Release and CI | .github/**, makefile, release_notes.txt, .fvmrc, pubspec.yaml |
version alignment, workflow blast radius, release sequencing |
| Migration reference | imported Kotlin/Swift/KMP files, migration notes, copied source snippets | behavior parity only; do not require KMP/iOS style rules in Flutter code |
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.
- 2d ago First seen · 183 lines · 65 tokens per session scan A db248cd04341
pr-review is a skill published in the GitHub repository strvcom/flutter-template (24 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 1,870 once invoked, about $0.0003 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…