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 blackwell-systems/agent-lsp --skill lsp-onboardgit clone --depth 1 https://github.com/blackwell-systems/agent-lspWrote 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/blackwell-systems/agent-lsp/lsp-onboard)<a href="https://agentmods.dev/skills/blackwell-systems/agent-lsp/lsp-onboard"><img src="https://agentmods.dev/badge/skills/blackwell-systems/agent-lsp/lsp-onboard/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/blackwell-systems/agent-lsp/lsp-onboard"><img src="https://agentmods.dev/badge/skills/blackwell-systems/agent-lsp/lsp-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.01191 |
| Opus 5 | $0.00023 | $0.00596 |
| Sonnet 5 | $0.00009 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
lsp-onboard 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 11d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lsp-onboard
First-session project onboarding. Run this when connecting to a new project for the first time. Explores the codebase via LSP tools and produces a structured project profile: languages, build system, test runner, entry points, key types, and architecture patterns.
The profile helps the agent make better decisions throughout the session without re-exploring the same ground. Run once per project; skip on subsequent sessions unless the project structure has changed significantly.
When to Use
- First time working in a new codebase
- After major structural changes (new packages, build system migration)
- When the agent seems confused about project conventions
Do NOT run this on every session. It's a one-time exploration.
Step 1: Detect languages and servers
mcp__lsp__detect_lsp_servers({ "workspace_dir": "<root>" })
Record which languages are present and which servers are available. This tells you what the project is built with.
Step 2: Initialize and verify
mcp__lsp__start_lsp({ "root_dir": "<root>" })
Wait for initialization. Call list_symbols on one key file to verify
the workspace is indexed.
Step 3: Identify entry points
Search for common entry point patterns:
mcp__lsp__find_symbol({ "query": "main" })
mcp__lsp__find_symbol({ "query": "Run" })
mcp__lsp__find_symbol({ "query": "Handler" })
Record entry points with their file paths. These are where execution starts.
Step 4: Map the package structure
For each top-level directory that contains source files, call list_symbols
on one representative file:
mcp__lsp__list_symbols({ "file_path": "<dir>/main.go", "format": "outline" })
Build a mental map: which packages exist, what they export, how they relate. Cap at 10 packages to avoid spending too long.
Step 5: Detect build and test commands
mcp__lsp__run_build({ "workspace_dir": "<root>" })
mcp__lsp__run_tests({ "workspace_dir": "<root>" })
Record whether build and tests pass, and what language/toolchain was detected. Note the test count and any failures.
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.
- 11d ago First seen · 160 lines · 45 tokens per session scan A b5f9f3051715
lsp-onboard is a skill published in the GitHub repository blackwell-systems/agent-lsp (124 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,191 once invoked, about $0.0002 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
analyze-usage
Use when asked to analyze codescout tool usage, check for error patterns, audit tool health, generate a usage report, spot anti-patterns, or clear usage statistics to start fresh.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
projectatlas
Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.
codex-coding-plugin
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
change-review
Use when reviewing a set of changes before they merge — a PR, a branch diff, or the working-tree changes you just made — in a Repowise-indexed codebase (.repowise/ directory exists). Activates for "review this PR", "is this safe to merge", "what's the blast radius of these changes", "did I miss anything", or "what…