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.
git clone --depth 1 https://github.com/asyncswap/skillsWrote 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/plugins/asyncswap/skills/lsp-bench)<a href="https://agentmods.dev/plugins/asyncswap/skills/lsp-bench"><img src="https://agentmods.dev/badge/plugins/asyncswap/skills/lsp-bench/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/plugins/asyncswap/skills/lsp-bench"><img src="https://agentmods.dev/badge/plugins/asyncswap/skills/lsp-bench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
lsp-bench 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.
What it actually says
{
"name": "lsp-bench",
"version": "0.1.0",
"description": "Test, validate, and benchmark performance of LSP servers using only YAML. Configs for benchmarks, response assertions, multi-file consistency checks, file-edit sequences, lifecycle tests, version comparisons, and LSP session management — restart per benchmark (cold) or reuse one initialized session across steps (warm).",
"author": {
"name": "Asyncswap Labs",
"email": "[email protected]",
"url": "https://github.com/asyncswap"
},
"homepage": "https://github.com/asyncswap/lsp-bench",
"repository": "https://github.com/asyncswap/lsp-bench",
"license": "MIT",
"keywords": [
"lsp",
"language-server",
"benchmark",
"solidity",
"performance",
"regression",
"correctness"
]
}
What it installs
The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 584 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill methods A 54 tokens
- Skill setup A 69 tokens
- Skill evolve-the-file A 53 tokens
- Skill lifecycle-tests A 63 tokens
- Skill multi-file A 51 tokens
- Skill replay A 51 tokens
- Skill assert-results A 40 tokens
- Skill cold-vs-warm A 56 tokens
- Skill commands A 0 tokens
- Skill custom-init-settings A 47 tokens
- Skill extra-files A 43 tokens
- Skill wait-for-token A 57 tokens
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 · 23 lines scan A 23f0133f65c0
lsp-bench is a plugin published in the GitHub repository asyncswap/skills (1 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
python-lsp
Claude Code plugin for Python development with Pyright LSP integration, 15 automated hooks for type checking, linting (ruff), formatting (black), testing (pytest), and security scanning.
crap-analyzer
Analyze recently-changed code for Change Risk Anti-Patterns. Computes CRAP per changed function across TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, and PHP. Auto-discovers how the repo generates coverage and proposes refactors + test stubs.
fuse-react
Expert React 19 with hooks, TanStack Router, TanStack Form, Zustand, Testing Library, shadcn/ui, and SOLID principles.
dev-loop
Multi-agent orchestration grounded in an LLM wiki. /dev-loop:orchestrate splits one goal into a dependency graph of parallel Claude Code sessions, each in its own worktree, and supervises them natively on Orca (a tracked Task + Dispatch per phase, pushed workerdone / question / escalation events instead of polling, st.
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
superpowers-orchestrator
Agentic development framework for Claude Code — disciplined workflow routing, TDD enforcement, safety hooks, systematic debugging, and code review.