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/benmarte/codemunch/detect-lspnpx skills add benmarte/codemunch --skill detect-lspgit clone --depth 1 https://github.com/benmarte/codemunchWhat 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 | $0.00050 | $0.01746 |
| Opus 5 | $0.00025 | $0.00873 |
| Sonnet 5 | $0.00010 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
detect-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 3d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LSP Detection Skill
Detect available language servers and configure codemunch to use them for precise symbol extraction.
Step 1 — Detect project languages
# Identify languages present in the project
find . -maxdepth 4 \( \
-name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.jsx" \
-o -name "*.py" \
-o -name "*.go" \
-o -name "*.rs" \
-o -name "*.rb" \
-o -name "*.java" -o -name "*.kt" \
-o -name "*.cs" \
-o -name "*.cpp" -o -name "*.c" -o -name "*.h" \
-o -name "*.php" \
-o -name "*.swift" \
-o -name "*.lua" \
-o -name "*.zig" \
-o -name "*.ex" -o -name "*.exs" \
-o -name "*.hs" \
-o -name "*.ml" -o -name "*.mli" \
\) -not -path "*/node_modules/*" -not -path "*/.git/*" \
-not -path "*/target/*" -not -path "*/__pycache__/*" \
2>/dev/null | \
sed 's/.*\.//' | sort | uniq -c | sort -rn | head -20
Step 2 — Check for installed language servers
For each detected language, check if a server is installed:
# TypeScript / JavaScript
which typescript-language-server 2>/dev/null && echo "LSP:typescript=typescript-language-server --stdio"
which tsserver 2>/dev/null && echo "LSP:typescript-alt=tsserver"
# Check via npx as fallback
npx --yes typescript-language-server --version 2>/dev/null && echo "LSP:typescript-npx=npx typescript-language-server --stdio"
# Python
which pylsp 2>/dev/null && echo "LSP:python=pylsp"
which pyright-langserver 2>/dev/null && echo "LSP:python=pyright-langserver --stdio"
which pyright 2>/dev/null && echo "LSP:python-alt=pyright --stdio"
which jedi-language-server 2>/dev/null && echo "LSP:python-alt2=jedi-language-server"
# Go
which gopls 2>/dev/null && echo "LSP:go=gopls"
# Rust
which rust-analyzer 2>/dev/null && echo "LSP:rust=rust-analyzer"
# Ruby
which solargraph 2>/dev/null && echo "LSP:ruby=solargraph stdio"
which ruby-lsp 2>/dev/null && echo "LSP:ruby-alt=ruby-lsp"
# Java
which jdtls 2>/dev/null && echo "LSP:java=jdtls"
which java-language-server 2>/dev/null && echo "LSP:java-alt=java-language-server"
# Kotlin
which kotlin-language-server 2>/dev/null && echo "LSP:kotlin=kotlin-language-server"
# C / C++
which clangd 2>/dev/null && echo "LSP:c=clangd"
which ccls 2>/dev/null && echo "LSP:c-alt=ccls"
# C#
which omnisharp 2>/dev/null && echo "LSP:csharp=omnisharp -lsp"
which csharp-ls 2>/dev/null && echo "LSP:csharp-alt=csharp-ls"
# PHP
which phpactor 2>/dev/null && echo "LSP:php=phpactor language-server"
which intelephense 2>/dev/null && echo "LSP:php-alt=intelephense --stdio"
# Swift
which sourcekit-lsp 2>/dev/null && echo "LSP:swift=sourcekit-lsp"
# Lua
which lua-language-server 2>/dev/null && echo "LSP:lua=lua-language-server"
# Zig
which zls 2>/dev/null && echo "LSP:zig=zls"
# Elixir
which elixir-ls 2>/dev/null && echo "LSP:elixir=elixir-ls"
which lexical 2>/dev/null && echo "LSP:elixir-alt=lexical"
# Haskell
which haskell-language-server 2>/dev/null && echo "LSP:haskell=haskell-language-server-wrapper --lsp"
which haskell-language-server-wrapper 2>/dev/null && echo "LSP:haskell=haskell-language-server-wrapper --lsp"
# OCaml
which ocamllsp 2>/dev/null && echo "LSP:ocaml=ocamllsp"
# Bash / Shell
which bash-language-server 2>/dev/null && echo "LSP:bash=bash-language-server start"
# YAML
which yaml-language-server 2>/dev/null && echo "LSP:yaml=yaml-language-server --stdio"
# JSON
which vscode-json-language-server 2>/dev/null && echo "LSP:json=vscode-json-language-server --stdio"
# CSS / HTML
which vscode-css-language-server 2>/dev/null && echo "LSP:css=vscode-css-language-server --stdio"
which vscode-html-language-server 2>/dev/null && echo "LSP:html=vscode-html-language-server --stdio"
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.
- 3d ago First seen · 178 lines · 50 tokens per session scan A ab2452fb6a58
detect-lsp is a skill published in the GitHub repository benmarte/codemunch (7 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 1,746 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 2026-08-31.
Other skills, from other repositories
karting-advisor
KartSan — AI karting coach for youth racers (7-14) in Rotax Micro/Mini/Junior MAX. Bilingual EN/PT. Analyzes MyChron 5/5S/6 telemetry, TRAX data, Race Studio 3 exports, GPS trails, and screenshots. Builds interactive dashboards with track maps and overlays. Covers technique, setup, gearing, tires, jetting, Rotax…
golden-rss
Use when testing the rss golden build.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.