Borrowing it
Nothing to install: this file belongs to p1va/symbols. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/p1va/symbols/main/.agents/skills/language-server-navigation/SKILL.mdgit clone --depth 1 https://github.com/p1va/symbolsWrote 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/skills/p1va/symbols/language-server-navigation)<a href="https://agentmods.dev/skills/p1va/symbols/language-server-navigation"><img src="https://agentmods.dev/badge/skills/p1va/symbols/language-server-navigation/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.
<a href="https://agentmods.dev/skills/p1va/symbols/language-server-navigation"><img src="https://agentmods.dev/badge/skills/p1va/symbols/language-server-navigation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.00617 |
| Opus 5.5 | $0.00018 | $0.00247 |
| Sonnet 5.5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
language-server-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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language Server Navigation
Use this skill when the codebase already has a relevant language server, or when the task should check that first. The goal is to use the current Language Servers tool surface deliberately instead of falling back to grep-driven workflows too early.
For a compact tool-selection cheat sheet, read references/tool-selection.md.
Workflow
- Check
language-servers://profilesfor a matching profile.- If there is no suitable profile, use the
install-language-serverskill.
- If there is no suitable profile, use the
- Start with the narrowest LSP-backed tool that answers the question.
outlinefor file structure and symbol locationsinspectfor symbol details and docsreferencesfor usagesrenamefor semantic renamesdiagnosticsfor compile or type errorscompletionfor API discovery at a pointsearchwhen the server supports language-aware search
- Use a real file path and precise line and character coordinates.
- If the user did not provide coordinates, use
outlinefirst to find them.
- If the user did not provide coordinates, use
- Treat file-backed tool calls as stateful.
- They can lazily start a dormant session.
- They can change the runtime state you see in the resources.
- If results look wrong, inspect:
language-servers://profiles/{name}language-servers://profiles/{name}/logs- then use
reloadonly if the config changed
Tool Choice Rules
- Prefer
renameover grep-based renames when a matching LSP exists. - Prefer
referencesover text search for call sites or symbol usage. - Prefer
inspectover opening arbitrary files when you need docs, types, or declaration context. - Use
searchonly when the server and current indexing state can support it. - Use plain text tools only when there is no working LSP profile or when the task is explicitly text-based.
Known Runtime Behaviors
not_startedafterreloadis normal. The first matching file-backed tool call should start the profile.- Search quality varies by server. TypeScript 7's native server does not normally need a preload anchor; the legacy
typescript-language-serverwrapper may still benefit from bounded, glob-basedpreload_filesentries. - Logs are best-effort. A running server may still have no window-log messages.
- Resources are the read surface. Use them for state and log inspection before guessing.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 54 lines · 44 tokens per session scan A 872d33cfef21
language-server-navigation is a skill published in the GitHub repository p1va/symbols (5 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 617 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
devcdp
How to debug a running web app with the DevCDP tools - connect to a tab, reload to capture, drive the page with the ui tools, set breakpoints that bind, and hand off to the user. Use whenever DevCDP tools are available and the task involves a web page, the browser, console or network output, or a front-end bug.
troubleshooter
Specialized in system-wide troubleshooting using metrics and logs.
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…