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 skills add alexei-led/architect --skill tools-lsp-tree-sittergit clone --depth 1 https://github.com/alexei-led/architectWrote 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/alexei-led/architect/tools-lsp-tree-sitter)<a href="https://agentmods.dev/skills/alexei-led/architect/tools-lsp-tree-sitter"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/tools-lsp-tree-sitter/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/alexei-led/architect/tools-lsp-tree-sitter"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/tools-lsp-tree-sitter.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 | $0.00102 | $0.00989 |
| Opus 5 | $0.00051 | $0.00495 |
| Sonnet 5 | $0.00020 | $0.00198 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
tools-lsp-tree-sitter 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LSP and tree-sitter
A language server resolves symbols the way the compiler does: it knows the real definition, every reference, the implementations of an interface, and the diagnostics the toolchain reports. tree-sitter parses syntax without resolution — fast, language-agnostic, but it cannot tell you what a name resolves to. Reach for LSP when you need semantic truth; fall back to tree-sitter when no server is configured.
Evidence dimensions: semantic (LSP) and structural (tree-sitter).
When to use
Use LSP to confirm a real call/reference relationship before claiming coupling, to find every implementation of a boundary interface, to verify callers/callees at a seam, and to surface compiler diagnostics. Use tree-sitter syntax queries when LSP is unavailable or when the question is purely syntactic (find all functions, all type declarations) and a server would be overkill.
Commands
LSP access depends on the runtime's LSP integration; use only exposed runtime operations, and do not invent tool names. Operations to request:
definition <file>:<line>:<col> # where a symbol is defined
references <file>:<line>:<col> # every use of a symbol
implementations <symbol> # implementors of an interface/abstract type
diagnostics <file|workspace> # compiler/linter diagnostics
documentSymbols <file> # outline of one file
workspaceSymbols <query> # find a symbol across the project
tree-sitter syntax queries (no resolution, pattern over the parse tree):
# Function definitions (Python grammar)
tree-sitter query func.scm src/**/*.py
# Inline: capture all class declarations
tree-sitter parse src/foo.py # inspect the tree to write a query
A .scm query file holds the capture patterns; run it across the target files.
Evidence output
Record:
dimension: semantic for LSP, structural for tree-sitter.source: operation, file:line:col or query file, and project/build context.facts: definitions, references, implementations, diagnostics, symbols, or syntax matches.limits: missing server, non-building project, partial workspace, or syntax-only fallback.
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.
- 9d ago First seen · 102 lines · 102 tokens per session scan A 0c60b4f80cdc
tools-lsp-tree-sitter is a skill published in the GitHub repository alexei-led/architect (2 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 989 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 2026-08-31.
Other skills, from other repositories
bug-detective
This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.
systematic-debugging
A four-phase method for investigating software bugs and test failures before changing code. It focuses on finding and confirming the underlying cause.
bensz-collect-bugs
A process for recording bugs caused by defects in Bensz skills. It stores a structured local report and can publish one only when the user explicitly asks.
grace-fix
Debug and fix issues in a GRACE 4 project using .grace semantic navigation, assertions, and verification evidence.
bug-fix-protocol
8-step disciplined bug-fix protocol that treats every production bug as two failures — the code defect itself and the testing system that allowed it through. Use when fixing a production bug, investigating a regression, writing a post-mortem, or auditing a missed defect. Triggers on "fix this bug", "production bug"…
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.