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/billbuchanan-code/claude-code-power-setup/flow.reviewnpx skills add billbuchanan-code/claude-code-power-setup --skill flow.reviewgit clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setupWhat 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 | $0.00016 | $0.04659 |
| Opus 5 | $0.00008 | $0.02329 |
| Sonnet 5 | $0.00003 | $0.00932 |
| Haiku 4.5 | $0.00002 | $0.00466 |
Grade A, and why
flow.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 — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Arguments:
- Empty: Run full interactive review with category-by-category approval
--dry-run: Generate findings without creating phase (preview mode)--categories <list>: Review only specified categories (comma-separated: BP,RF,HD,MF,OC,OE,OD,SC,UI)--fix: Auto-approve findings with effort ≤4, defer effort=5 items, then auto-run/flow.orchestrate
You MUST consider the user input before proceeding (if not empty).
Note: Use specflow directly, NOT npx specflow. It's a local CLI at ~/.claude/specflow-system/bin/.
Prerequisites
| Requirement | Check Command | If Missing |
|---|---|---|
| ROADMAP.md exists | cat ROADMAP.md |
Run /flow.roadmap |
| Constitution | .specify/memory/constitution.md |
Run /flow.init |
| Codebase to review | ls -la |
Need code to review |
| Git repo | git status |
Initialize git repo |
Goal
Perform a systematic code review across 7 categories, generate findings with effort/impact/severity ratings, allow interactive user approval, create an implementation phase for approved items, and defer rejected items to the backlog.
This is a refinement workflow focused on:
- Implementing coding best practices
- Identifying refactoring opportunities
- Recommending hardening improvements
- Finding missing/incomplete features
- Cleaning up orphaned code
- Simplifying over-engineered solutions
- Updating outdated documentation
Constraints:
- Does NOT propose brand new features
- Does NOT break existing functionality without confirmation
- Focus on technical debt reduction and code quality
Review Categories
| Code | Category | Focus |
|---|---|---|
| BP | Best Practices | Coding standards violations, anti-patterns, inconsistencies |
| RF | Refactoring | Code duplication, complex functions (>100 lines), poor structure |
| HD | Hardening | Error handling gaps, input validation, security patterns |
| MF | Missing Features | TODOs, FIXMEs, stub functions, incomplete implementations |
| OC | Orphaned Code | Unused exports, dead code, unreferenced files |
| OE | Over-Engineering | Excessive abstraction, unused flexibility, premature optimization |
| OD | Outdated Docs | Stale comments, README mismatches, incorrect examples |
| SC | Spec Compliance | Implementation doesn't match spec.md requirements (if phase artifacts exist) |
| UI | UI Compliance | UI doesn't match ui-design.md mockups (if ui-design.md exists) |
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 · 614 lines · 16 tokens per session scan A 07cb11216603
flow.review is a skill published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 4,659 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 2026-08-31.
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…