code-review-with-lsp

code-review-with-lsp is a skill for Claude Code, Codex from liuyanghejerry/Clausura. It costs 40 tokens per session (546 once invoked), scanned A, original, MIT.

A code-review method that uses language-server tools to understand code symbols, types, definitions and diagnostics. A language server is a program that provides editor-like knowledge about a programming language.

In plain words
What is it for?
Checking diagnostics, looking up unfamiliar functions or types, tracing where symbols are defined and finding all places that use them.
Why use it?
It finds problems and possible side effects that simple text searches may miss, especially when a change affects shared code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Checking diagnostics, looking up unfamiliar functions or types, tracing where symbols are defined and finding all places that use them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liuyanghejerry/clausura/code-review-with-lsp
Install

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.

Any agent
npx skills add liuyanghejerry/Clausura --skill code-review-with-lsp
Clone the repo
git clone --depth 1 https://github.com/liuyanghejerry/Clausura

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 code-review-with-lsp

README.md
[![agentmods](https://agentmods.dev/badge/skills/liuyanghejerry/clausura/code-review-with-lsp/github.svg)](https://agentmods.dev/skills/liuyanghejerry/clausura/code-review-with-lsp)
Your own site
<a href="https://agentmods.dev/skills/liuyanghejerry/clausura/code-review-with-lsp"><img src="https://agentmods.dev/badge/skills/liuyanghejerry/clausura/code-review-with-lsp/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.

agentmods 80×15 button for code-review-with-lsp

Your own site · 80×15
<a href="https://agentmods.dev/skills/liuyanghejerry/clausura/code-review-with-lsp"><img src="https://agentmods.dev/badge/skills/liuyanghejerry/clausura/code-review-with-lsp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 546 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 $0.00040 $0.00546
Opus 5 $0.00020 $0.00273
Sonnet 5 $0.00008 $0.00109
Haiku 4.5 $0.00004 $0.00055

Measured 11d ago against content hash cd29d212d2f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

code-review-with-lsp 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 11d 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.

examples/skills/code-review-with-lsp/SKILL.md · 67 lines

What it actually says

Code Review with LSP

This skill works with mcp_servers + preflight in .clausura.yaml. Preflight diagnostics are collected automatically; this skill guides the agent to use LSP tools for deeper semantic analysis.

Review Workflow

For each file or diff hunk under review:

Step 1. Check diagnostics

Call mcp__<server>__get_diagnostics (or equivalent) for the file. Preflight results are already in context — but if diagnostics were not automatically collected, run them now.

Record every diagnostic as a finding:

  • rule_id: lsp-<diagnostic-type> (e.g. lsp-type-mismatch)
  • severity: map 1:1 from diagnostic severity
  • message: keep the original diagnostic message verbatim

Step 2. Understand unfamiliar symbols

When you encounter a symbol, function, or type you need to understand:

  1. hover — get type signature and docs: mcp__<server>__hover
  2. definition — jump to the definition: mcp__<server>__goto_definition
  3. references — check all callers: mcp__<server>__find_references

Step 3. Check for cascading impact

If a change affects a public API or core type:

  • Use mcp__<server>__find_references to find all callers
  • Check if those callers handle the new signature correctly

Finding Severity Mapping

LSP Severity Finding Severity When
Error error Compile error, type mismatch, undefined reference
Warning warning Deprecation, unused variable, non-fatal lints
Information info Style hints, auto-fix suggestions
Hint hint Minor suggestions, organizational hints

Example Rule IDs for Gating

gating:
  # LSP diagnostics (rule_id_prefix: "lsp-")
  - rule: lsp-type-mismatch
    min_severity: error
    max_findings: 0
    action: fail
  - rule: lsp-compile-error
    min_severity: error
    max_findings: 0
    action: fail
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. 11d ago First seen · 67 lines · 40 tokens per session scan A cd29d212d2f3

Subscribe to this mod's changes

code-review-with-lsp is a skill published in the GitHub repository liuyanghejerry/Clausura (203 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 546 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.