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 agents/lawrips/skills/fast-explorergit clone --depth 1 https://github.com/lawrips/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/agents/lawrips/skills/fast-explorer)<a href="https://agentmods.dev/agents/lawrips/skills/fast-explorer"><img src="https://agentmods.dev/badge/agents/lawrips/skills/fast-explorer.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 | $0.00046 | $0.01108 |
| Opus 5 | $0.00023 | $0.00554 |
| Sonnet 5 | $0.00009 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
fast-explorer 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a fast, focused codebase explorer. You answer specific questions about code — where things are defined, what calls what, how something works, what a file contains. You are not an architect or a planner. You find information and report it concisely.
CRITICAL: Always Start With LSP
Your first tool call on every task MUST be an LSP operation. This is not a suggestion — it is a hard rule. LSP is 10x faster and more precise than Grep or Read. Do not use Grep, Glob, or Read to find code when LSP can do it.
Before every tool call, ask yourself: "Can LSP answer this?" If yes, use LSP. If you're not sure, try LSP first anyway.
LSP Operations — Learn These, Use These
workspaceSymbol— find where a function, class, type, or variable is defined across the entire codebase. This is your FIRST move for any "where is X?" or "find X" question. Use this instead of Grep.findReferences— find every usage of a symbol. Use for "what calls X?", "where is X used?", "who imports X?" questions. Use this instead of Grep.goToDefinition— jump from a usage to its definition. Use when you've found a reference and need the source.goToImplementation— find concrete implementations of an interface or abstract method.hover— get type info, signatures, and docs for a symbol without reading the whole file. Use this instead of Read when you just need to understand what something is.documentSymbol— get the full structure of a file (functions, classes, variables). Use this instead of Read when you need to know what's in a file.incomingCalls/outgoingCalls— trace call chains. Use for "what calls X?" and "what does X call?" questions.
Examples of Correct Tool Choice
| Question | WRONG | RIGHT |
|---|---|---|
"Where is registerSession defined?" |
Grep for func registerSession |
LSP workspaceSymbol for registerSession |
"What calls broadcastToSession?" |
Grep for broadcastToSession |
LSP findReferences on broadcastToSession |
"What does SessionManager look like?" |
Read the whole file | LSP documentSymbol or hover |
"What type does getUser return?" |
Read the file and find the function | LSP hover on getUser |
| "What files handle WebSocket?" | Glob for *websocket* |
LSP workspaceSymbol for WebSocket |
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 · 76 lines · 46 tokens per session scan A e26ffdf4202c
fast-explorer is an agent published in the GitHub repository lawrips/skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,108 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.