fallow: Skill for Claude Code

.agents/skills/lsp-review/SKILL.md

lsp-review is a skill for Claude Code, Codex from fallow-rs/fallow. It costs 39 tokens per session (105 once invoked), scanned A, original, MIT.

A review checklist for an LSP server, the part of a code editor integration that provides diagnostics, code actions, code lenses, and other editor features. It checks both protocol behavior and the editor experience.

In plain words
What is it for?
Use it when changing the LSP server or any behavior visible through the editor. The review ends with an approval, concern, or block decision.
Why use it?
It helps catch incorrect messages, unstable behavior, unclear diagnostics, and awkward editor interactions before release.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is fallow-rs/fallow's own configuration. It tells Claude Code and Codex how to work on fallow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fallow configures →

About the project

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.

fallow-rs/fallow · 4,461 stars · on GitHub · docs.fallow.tools

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/fallow-rs/fallow/main/.agents/skills/lsp-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fallow-rs/fallow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lsp-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/fallow-rs/fallow/lsp-review.svg)](https://agentmods.dev/skills/fallow-rs/fallow/lsp-review)
Your own site
<a href="https://agentmods.dev/skills/fallow-rs/fallow/lsp-review"><img src="https://agentmods.dev/badge/skills/fallow-rs/fallow/lsp-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00105
Opus 5 $0.00019 $0.00053
Sonnet 5 $0.00008 $0.00021
Haiku 4.5 $0.00004 $0.00011

Measured 8d ago against content hash 17b0962de275, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lsp-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 8d 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.

.agents/skills/lsp-review/SKILL.md · 15 lines

What it actually says

LSP Review

Read:

  • .agents/agents/lsp-reviewer.md
  • .agents/rules/lsp-server.md

Focus on protocol correctness, diagnostic quality, stable behavior, and editor-facing usability.

End with APPROVE, CONCERN, or BLOCK.

Changes

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.

  1. 8d ago First seen · 15 lines · 39 tokens per session scan A 17b0962de275

Subscribe to this mod's changes

lsp-review is a skill published in the GitHub repository fallow-rs/fallow (4,461 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 105 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.