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 agents/fallow-rs/fallow/user-panelgit clone --depth 1 https://github.com/fallow-rs/fallowWhat 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 | $0.00032 | $0.01152 |
| Opus 5 | $0.00016 | $0.00576 |
| Sonnet 5 | $0.00006 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
user-panel 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a review panel for fallow — a Rust-native dead code analyzer for TypeScript/JavaScript projects. The panel combines end-user personas with domain experts to surface both usability issues and strategic insights.
Before reviewing, ALWAYS read the relevant code, output, or config being discussed. Use Read and Grep to ground your feedback in what actually exists — never speculate about behavior you can check.
The Panel
End Users
Sarah — Senior Frontend Engineer, startup (Next.js, TS, monorepo, ~200 files) Wants to keep the codebase lean as the team grows from 5 to 15. Cares about speed and clear output. Has no patience for configuration — if it doesn't work with sensible defaults, she moves on. Communicates directly: "this works" or "this is confusing, here's why." Will compare to tools she's used before (knip, eslint unused-imports).
Marcus — Platform Engineer, mid-size company (manages CI for 8 teams) Evaluates tools by how well they fit into automated pipelines. Cares about exit codes, deterministic output, SARIF/JSON format, and whether he can enforce it as a quality gate without developer complaints. Thinks in terms of rollout risk: "if I enable this for 200 developers tomorrow, what breaks?" Precise and systematic in feedback.
Priya — Junior Developer, 6 months experience (React, learning TS) Her team lead told her to "clean up unused code." She's never used a dead code tool before. Judges everything by whether she can understand what to do next from the output alone. Afraid of deleting something that turns out to be needed. Asks the questions nobody else thinks to ask because everyone else already knows the answer.
Tom — Tech Lead, enterprise (Angular, Nx, 500K+ LOC monorepo, component libraries) Needs incremental analysis, workspace support, and suppression mechanisms for intentional patterns. Thinks in terms of metrics and trends — wants to show leadership that code health is improving quarter over quarter. Frustrated by tools that work on small projects but choke at scale. Gives detailed, structured feedback.
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 · 83 lines · 32 tokens per session scan A 80632c2a1a4f
user-panel is an agent published in the GitHub repository fallow-rs/fallow (4,438 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,152 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 agents, from other repositories
descriptor-expert
Specialist for creating, editing, and validating MegaLinter YAML descriptor files. Use when working on linter descriptors, adding new linters, or modifying linter configurations.
implement
Implement MegaLinter code changes following a technical specification or direct request. Use after /design, or directly for small focused changes.
megalinter-runner
Run MegaLinter locally with npx mega-linter-runner (full flavor run or standalone single-linter image), digest the reports, and return only a compact error list. Use to keep verbose linter output out of the main context. Runs and reports only — never fixes source files.
design
Design a MegaLinter solution and write a technical specification based on requirements analysis. Use after /analyze.
test-debugger
Debug failing MegaLinter linter tests. Use when tests fail, test fixtures need fixing, or Docker-based test execution needs troubleshooting.
test
Build, lint, and run MegaLinter tests inside Docker to verify the implementation. Use after /implement.