Fallow is a command-line static-analysis tool that builds a dependency graph of TypeScript and JavaScript code to identify unused code, duplication, circular dependencies, complexity hotspots, boundary violations, and styling drift. It is for developers reviewing codebases and verifying changes, with catalogue entries that add agent, editor, and workflow integrations.
Borrowing it
Nothing to install: this file belongs to fallow-rs/fallow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fallow-rs/fallow/main/.agents/skills/panel-review/SKILL.mdgit clone --depth 1 https://github.com/fallow-rs/fallowWrote 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/fallow-rs/fallow/panel-review)<a href="https://agentmods.dev/skills/fallow-rs/fallow/panel-review"><img src="https://agentmods.dev/badge/skills/fallow-rs/fallow/panel-review/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/fallow-rs/fallow/panel-review"><img src="https://agentmods.dev/badge/skills/fallow-rs/fallow/panel-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00255 |
| Opus 5.5 | $0.00014 | $0.00102 |
| Sonnet 5.5 | $0.00007 | $0.00051 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
panel-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 1mo 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.
What it actually says
Panel review
- Read the controlling plan or specification first.
- Build one evidence package from current source, live behavior, and relevant public contracts.
- Select representative users plus specialists for accessibility, security, privacy, compatibility, operations, or agent runtimes as applicable.
- Ask reviewers for concrete blockers, concerns, follow-ups, and no-action decisions.
- Verify load-bearing claims against source before accepting them.
- Filter the findings first. Drop style preferences and "a different design would also work" unless the reviewer shows a concrete problem. Trace a call site before you accept a bug claim. Put each dropped finding under No action with one reason.
- Synthesize consensus under:
- Fix before change
- Fix now
- Follow-up
- No action
- Record approved decisions in the active
.plans/<task>.md.
Do not expose private source text or internal review labels in public output. Panel feedback is evidence, not authority over tested contracts.
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.
- 1mo ago Changed · +4 lines 883dc696808a
- 2mo ago First seen · 25 lines · 34 tokens per session scan A a9ecbc0c2324
panel-review is a skill published in the GitHub repository fallow-rs/fallow (5,273 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 255 once invoked, about $0.0001 per session on Opus 5.5. 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
qcad
Use when editing or batch-converting DXF/DWG drawings with QCAD 3.33 — RAddObjectsOperation scripting, dwginfo/dwg2pdf/dwg2svg console tools, or version conversion through qcad -no-gui -autostart SaveAs.js -filter; also when dwg2pdf/dwg2svg are missing because they ship only with QCAD Professional, when a PDF export…
cli-forge-choice-ux
Design, audit, and simplify user choice flows: checkout, purchase, ordering, pricing selection, signup, onboarding, settings, configuration wizards, plan pickers, product configurators, forms, and any interface where users must decide, configure, buy, subscribe, or complete a guided task. Use when the user says UX…
cli-forge-schema
Use this skill to generate, convert, or refine diagrams and visual representations in GitHub-compatible Mermaid. Triggers include: 'diagram', 'schema', 'flowchart', 'sequence diagram', 'architecture diagram', 'ER diagram', 'state machine', 'gantt', 'mindmap', 'timeline', 'mermaid', 'visualize', 'draw', 'convert table…
cli-audit-wizard
Audit configuration wizard UX and lifecycle quality (setup, doctor, edit, migrate). Scores the 4 Laws (ask once, defaults, recap, config-as-code), credential discovery, multi-surface consistency (CLI/MCP/web), and scriptability. Detects wizard anti-patterns. Use on 'wizard', 'setup flow', 'config UX', 'init command'…
biome
Biome - Fast all-in-one toolchain for web projects (linter + formatter in Rust, 100x faster than ESLint).
swiss-shot-demos
A skill for making video storyboard animations as standalone HTML scenes in a Swiss graphic-design style. Each scene uses a content-matched chart or diagram, such as a timeline, flow, comparison, or matrix.