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 skills/zircote/lsp-tools/lsp-enablenpx skills add zircote/lsp-tools --skill lsp-enablegit clone --depth 1 https://github.com/zircote/lsp-toolsWrote 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/zircote/lsp-tools/lsp-enable)<a href="https://agentmods.dev/skills/zircote/lsp-tools/lsp-enable"><img src="https://agentmods.dev/badge/skills/zircote/lsp-tools/lsp-enable.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 | $0.00098 | $0.02263 |
| Opus 5 | $0.00049 | $0.01131 |
| Sonnet 5 | $0.00020 | $0.00453 |
| Haiku 4.5 | $0.00010 | $0.00226 |
Grade A, and why
lsp-enable 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 5d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LSP-First Code Intelligence
The Iron Laws
1. NO MODIFYING UNFAMILIAR CODE WITHOUT goToDefinition FIRST
2. NO REFACTORING WITHOUT findReferences IMPACT ANALYSIS FIRST
3. NO CLAIMING CODE WORKS WITHOUT LSP DIAGNOSTICS VERIFICATION
Violating these laws wastes tokens, introduces bugs, and produces incomplete changes.
Trigger Phrases
Activate when user says:
- "find definition", "go to definition", "where is X defined"
- "find references", "who uses this", "what calls this function"
- "understand this code", "trace this function", "explore codebase"
- "before I refactor", "impact of changing", "safe to rename"
- "analyze dependencies", "call hierarchy", "incoming calls"
- "check this code", "verify implementation", "LSP diagnostics"
Core Decision Tree
WHAT DO YOU NEED?
│
├─ Symbol definition or implementation
│ └─ USE LSP: goToDefinition, goToImplementation
│
├─ All usages of a symbol
│ └─ USE LSP: findReferences
│
├─ Type info, docs, or signatures
│ └─ USE LSP: hover
│
├─ File structure or symbol list
│ └─ USE LSP: documentSymbol
│
├─ Call graph or dependencies
│ └─ USE LSP: incomingCalls, outgoingCalls
│
├─ Symbol search across workspace
│ └─ USE LSP: workspaceSymbol
│
├─ Literal text search (TODOs, strings, config)
│ └─ USE: Grep (LSP doesn't do text matching)
│
└─ File discovery by pattern
└─ USE: Glob
The Nine LSP Operations
| Operation | Purpose | Use Before |
|---|---|---|
goToDefinition |
Jump to where symbol is defined | Modifying unfamiliar code |
findReferences |
Find all usages of a symbol | Refactoring, renaming |
goToImplementation |
Find interface implementations | Working with polymorphism |
hover |
Get type info, docs, signatures | Understanding APIs |
documentSymbol |
List all symbols in a file | Understanding large files |
workspaceSymbol |
Search symbols across codebase | Finding related code |
prepareCallHierarchy |
Get call hierarchy info | Analyzing call graphs |
incomingCalls |
Find callers of a function | Impact analysis |
outgoingCalls |
Find functions called by target | Dependency tracing |
What ships with it
30 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.
- references/cpp-hooks.json 1.8 KB
- references/cpp-lsp-section.md 2.4 KB
- references/csharp-hooks.json 1.2 KB
- references/csharp-lsp-section.md 2.0 KB
- references/go-hooks.json 1.5 KB
- references/go-lsp-section.md 2.1 KB
- references/html-css-hooks.json 1.6 KB
- references/html-css-lsp-section.md 2.0 KB
- references/java-hooks.json 1.8 KB
- references/java-lsp-section.md 2.2 KB
- references/kotlin-hooks.json 1.3 KB
- references/kotlin-lsp-section.md 1.9 KB
- references/latex-hooks.json 1.2 KB
- references/latex-lsp-section.md 2.2 KB
- references/lsp-decision-matrix.md 5.2 KB
- references/lsp-enforcement-protocol.md 5.5 KB
- references/lsp-operations-guide.md 5.7 KB
- references/lsp-server-registry.md 10 KB
- references/lsp-setup-verification.md 6.1 KB
- references/php-hooks.json 1.7 KB
- references/php-lsp-section.md 2.1 KB
- references/python-hooks.json 1.6 KB
- references/python-lsp-section.md 1.9 KB
- references/ruby-hooks.json 1.3 KB
- references/ruby-lsp-section.md 1.9 KB
- references/rust-hooks.json 1.7 KB
- references/rust-lsp-section.md 2.1 KB
- references/SETUP-GUIDE-ALL-LANGUAGES.md 7.0 KB
- references/typescript-hooks.json 1.6 KB
- references/typescript-lsp-section.md 1.9 KB
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.
- 5d ago First seen · 264 lines · 98 tokens per session scan A bd7b1d5f11d1
lsp-enable is a skill published in the GitHub repository zircote/lsp-tools (12 stars, last pushed 26d ago), licensed MIT. It adds 98 tokens to every session and 2,263 once invoked, about $0.0005 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 skills, from other repositories
mako-discovery
TRIGGER when: user is working in an unfamiliar repo, asks 'where is X', 'what touches Y', needs broad search across code/schema/routes, or is unsure which mako tool fits the task. Covers reefask, reefstatus, reefverify, reefimpact, makohelp, toolsearch, contextpacket, livetextsearch, lintfiles, and toolbatch.
mako-code-intel
TRIGGER when: user wants structural code pattern search (ast-grep) or static lint against selected files, or wants to turn a fix diff into a rule-pack draft. Covers astfindpattern, lintfiles, extractruletemplate.
mako-guide
Start here when working in a project with the mako-ai MCP server configured. Entry point that explains how mako's tool skills are organized and carries the policy for logging agentfeedback vs acknowledging static findings with findingack.
mako-workflow
TRIGGER when: user wants an investigation packet, pre-ship artifact, recall of prior work or answers, or to log tool-run feedback / inspect telemetry. Covers suggest, investigate, workflowpacket, tenantleakaudit, healthtrend, issuesnext, sessionhandoff, all four artifact tools, recallanswers, recalltoolruns…
mako-graph
TRIGGER when: user asks about relationships, dependency paths, import hotspots or cycles, symbol impact, or blast radius of a proposed change. Covers graphneighbors, graphpath, flowmap, changeplan, importsdeps, importsimpact, importshotspots, importscycles, symbolsof, exportsof.
mako-trace
TRIGGER when: user asks to trace a specific route, schema object, file, table, RPC, or error string through its evidence. Covers routetrace, schemausage, filehealth, authpath, tracefile, preflighttable, traceedge, traceerror, tracetable, tracerpc.