lsp-navigation

lsp-navigation is a skill for Claude Code, Codex from Zfinix/aster. It costs 53 tokens per session (384 once invoked), scanned A, original, Apache-2.0.

A set of code-navigation and quick error-checking tools based on a language server, which is a program that understands a programming language's structure. It can check edited code, find real uses of a symbol, and jump to its definition.

In plain words
What is it for?
Use it to check whether an edit introduced errors, find where a function or variable is used, or open the source definition behind a call.
Why use it?
It avoids running a full build after every small edit and avoids unreliable text searches that also match comments, strings, or unrelated names.

Skill for Claude CodeCodex

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

Good fit Use it to check whether an edit introduced errors, find where a function or variable is used, or open the source definition behind a call.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zfinix/aster/lsp-navigation
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 Zfinix/aster --skill lsp-navigation
Clone the repo
git clone --depth 1 https://github.com/Zfinix/aster

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-navigation

README.md
[![agentmods](https://agentmods.dev/badge/skills/zfinix/aster/lsp-navigation.svg)](https://agentmods.dev/skills/zfinix/aster/lsp-navigation)
Your own site
<a href="https://agentmods.dev/skills/zfinix/aster/lsp-navigation"><img src="https://agentmods.dev/badge/skills/zfinix/aster/lsp-navigation.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 384 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 $0.00053 $0.00384
Opus 5 $0.00026 $0.00192
Sonnet 5 $0.00011 $0.00077
Haiku 4.5 $0.00005 $0.00038

Measured yesterday against content hash 166741dd6e3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lsp-navigation 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 yesterday.

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.

crates/aster-skills/builtins/internal/lsp-navigation/SKILL.md · 28 lines

What it actually says

LSP navigation

  1. lsp_diagnostics beats a full build for "did my edit compile". After editing a file, one diagnostics call answers it in milliseconds. A full cargo check or tsc run is for the end of a task, not every edit.
  2. lsp_references finds real usages. Text search finds the name in comments, strings, and unrelated scopes; references finds call sites. Use it before renaming or deleting anything. It takes a file plus a position, so search for the symbol first, then pass the position of one hit.
  3. lsp_definitions jumps to the source. Use it when a call site's types are unclear and you need the signature, instead of guessing the file path and reading it.
  4. Line and character are zero-based. The positions come from the file itself; if you just read the file, the line you saw is already the right number minus one.
  5. The first call in a language is slow. The server starts and indexes on first use; rust-analyzer can take seconds on a large crate. That is startup cost, not a hang. Subsequent calls in the same session reuse the running server.
  6. Missing servers are expected. If a tool says the language server is not installed, fall back to text search and a build; do not retry or tell the user to install anything unless they ask.
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. yesterday First seen · 28 lines · 53 tokens per session scan A 166741dd6e3f

Subscribe to this mod's changes

lsp-navigation is a skill published in the GitHub repository Zfinix/aster (57 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 384 once invoked, about $0.0003 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 2026-09-06.

Related

Other skills, from other repositories