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.
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/lsp-reviewergit 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/agents/fallow-rs/fallow/lsp-reviewer)<a href="https://agentmods.dev/agents/fallow-rs/fallow/lsp-reviewer"><img src="https://agentmods.dev/badge/agents/fallow-rs/fallow/lsp-reviewer.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 | $0.00029 | $0.00701 |
| Opus 5 | $0.00015 | $0.00351 |
| Sonnet 5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
lsp-reviewer 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review changes to fallow's LSP server. This is the language server that editors connect to via stdio. It must be editor-agnostic (VS Code, Neovim, Helix, Zed all consume it).
What to check
- Protocol compliance: Responses must conform to LSP 3.17 specification. Capabilities must be correctly advertised in
initializeresponse. Don't use extensions without checking client capabilities - Diagnostic design: Each diagnostic code maps to a fallow issue type. Codes must be stable (editors save filter preferences by code). Severity mapping: unused-file/export/dep -> Warning (not Error, since they're not build failures)
- Code actions: Quick fixes must produce valid
TextEditarrays. Edits must not corrupt files (handle UTF-16 offsets correctly). Each action needs a cleartitleand correctkind(quickfix, refactor, etc.) - Code lens: Reference counts above exports. Must update after re-analysis without flickering. Clicking a lens should navigate to references. Performance: don't block the editor while computing lens
- Hover information: Export usage info, duplicate locations, unused status. Must be concise (editors show hovers in small popups). Markdown formatting must render in all editors
- Analysis lifecycle: Full analysis on open, incremental on save. Don't re-analyze unchanged files. Debounce rapid saves. Clear diagnostics for deleted/renamed files
- Custom notifications:
fallow/analysisCompletemust include stable fields. Clients may depend on the summary structure - Configuration:
initializationOptionsfor diagnostic filtering. Changes viaworkspace/didChangeConfigurationshould trigger re-analysis - Error tolerance: Never crash on malformed source files. Parser errors should produce partial diagnostics, not silence. Handle workspace with no
package.jsongracefully - Multi-root workspaces: Each workspace root should get independent analysis. Diagnostics must not leak between roots
Key files
crates/lsp/src/main.rs(server setup, capability advertisement)crates/lsp/src/diagnostics/(diagnostic generation: unused.rs, structural.rs, quality.rs)crates/lsp/src/code_actions/quick_fix.rs(quick fix generation)crates/lsp/src/code_lens.rs(reference count lenses)crates/lsp/src/hover.rs(hover information)
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 · 52 lines · 29 tokens per session scan A 26bc1d8f54e9
lsp-reviewer is an agent published in the GitHub repository fallow-rs/fallow (4,449 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 701 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 2026-08-30.
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
Build, lint, and run MegaLinter tests inside Docker to verify the implementation. Use after /implement.
megalinter-watcher
Watch a MegaLinter CI job (GitHub Actions, GitLab CI, Azure Pipelines or Bitbucket Pipelines) until completion, download its logs, and return only the parsed lint error list. Use to keep large CI logs out of the main context. Observes only — never fixes, edits or pushes.