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 wsauret/flywheel --skill work-reviewgit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/wsauret/flywheel/work-review)<a href="https://agentmods.dev/skills/wsauret/flywheel/work-review"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/work-review.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.04089 |
| Opus 5 | $0.00023 | $0.02044 |
| Sonnet 5 | $0.00009 | $0.00818 |
| Haiku 4.5 | $0.00005 | $0.00409 |
Grade A, and why
work-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 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Reviewing Skill
Perform exhaustive code reviews using multi-agent analysis. Collect each reviewer's prose findings, structure them into the schema, dedup semantically, and write a merged review.findings.json into the active session directory.
Architecture: Reviewers return natural-language prose; the synthesizer (this skill) is the single schema enforcer. Reviewers focus on finding issues; structuring is the synthesizer's job.
Input
The review target is provided via $ARGUMENTS. Can be:
- PR number (numeric):
123 - GitHub URL:
https://github.com/org/repo/pull/123 - Branch name:
feature/my-branch - Empty: review current branch changes
The active session is resolved via .flywheel/plugin/active.json. If that file is missing, error with:
No active session. Run /plan first.
Phase 0: Setup
Determine review target
git branch --show-current
# If PR number:
gh pr view <PR_NUM> --json title,body,files
Setup environment
- If already on target branch: proceed with analysis.
- If different branch: offer to check out the target branch or create a worktree with
git worktree add.
Ensure the code is ready for analysis before dispatching reviewers.
Discover project context
Use Glob to find architectural docs once at the orchestrator level — reviewers consume the resulting paths instead of doing parallel discoveries:
CLAUDE.mdagents.mddocs/architecture.mddocs/adrs/**/*.mddocs/coding-guidelines*.md
Collect the matching paths into PROJECT_CONTEXT_PATHS. Inline them in every reviewer dispatch under "PROJECT CONTEXT PATHS." If no docs match, pass none — reviewers skip discovery and apply universal principles only.
Phase 1: Dispatch Reviewer Agents
Launch Task for every reviewer in a SINGLE message. Each Task prompt MUST include:
- The diff / PR content inline (or a reference the reviewer can read)
- Code-scope location format:
<repo-relative-path>or<repo-relative-path>:<line> - The no-file-write constraint (reviewers return prose; synthesizer handles all file writes)
- The active session's spec rationale (inlined from
spec.context) — reviewers must distinguish implementer error from plan-prescribed shape
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 · 355 lines · 46 tokens per session scan A 453b1cc17a8f
work-review is a skill published in the GitHub repository wsauret/flywheel (14 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 4,089 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
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-compile-issues
Triage N GitHub issues into a coverage matrix: fetch each, check current code, classify already-done/quick-fix/design/defer with cited evidence.
review
Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.
simplify
Improve clarity and reduce needless complexity after behavior is understood; preserve behavior and keep cleanup separate from correctness fixes.
code-review
Run a thorough self-review pass on the most recent change.
refine-tests
Reviews existing test code for conformance to the test-designing-guide and test-writing-guide, then applies the refinements. Use this skill when the user wants to review or refine existing test code so it follows the project's test design and writing conventions. Typically invoked as /refine-tests .