/fast-queries
Use when diagnosing an issue, checking system health, or validating state before deeper investigation
Claude Code
$ npx -y skills add metraton/gaia --skill fast-queries --agent claude-code
Codex
$ npx skills add metraton/gaia --skill fast-queries -a codex -y
Cursor
$ npx skills add metraton/gaia --skill fast-queries -a cursor -y
Gemini CLI
$ npx skills add metraton/gaia --skill fast-queries -a gemini-cli -y
GitHub Copilot
$ npx skills add metraton/gaia --skill fast-queries -a github-copilot -y
OpenCode
$ npx skills add metraton/gaia --skill fast-queries -a opencode -y
Windsurf
$ npx skills add metraton/gaia --skill fast-queries -a windsurf -y
SKILL.md
fast-queries.SKILL.mdname: fast-queries
description: Use when diagnosing an issue, checking system health, or validating state before deeper investigation
Fast Queries
Start with supplied evidence, not a fixed diagnostic script.
1. Read the injected dispatch kernel: `# Your Contract` (goal, `project`, your `can_read` menu) and `# Project context`, the dispatch project's `can_read` sections, whole when they fit, else one `get-contract` pointer per section, else a single count line. A component the goal names that the block does not carry is fetched first (`investigation`, evidence ladder step 1). 2. Pull the rest of what the goal needs from the persistent substrate, narrowly scoped. The read vocabulary -- which verb opens which coordinate, what each returns, and the workspace rule -- is in `agent-protocol/read-map.md`. 3. Run the smallest authoritative read-only CLI query for the surfaced domain. Use native output/filter flags and one command per call. 4. Record the query, result, and uncertainty in the contract checkpoint. 5. Deep-dive only where the evidence identifies a gap or inconsistency.
Do not invoke helpers from `.claude/`; that tree is an installed/protected surface, not Gaia source. Do not treat a broad health command's exit code as proof of a specific desired state. If investigation forecasts mutation, switch to `investigation` and collect predictable exact T3 commands before requesting consent.
Read more
name: fast-queries description: Use when diagnosing an issue, checking system health, or validating state before deeper investigation
Fast Queries
Start with supplied evidence, not a fixed diagnostic script.
1. Read the injected dispatch kernel: `# Your Contract` (goal, `project`, your `can_read` menu) and `# Project context`, the dispatch project's `can_read` sections, whole when they fit, else one `get-contract` pointer per section, else a single count line. A component the goal names that the block does not carry is fetched first (`investigation`, evidence ladder step 1). 2. Pull the rest of what the goal needs from the persistent substrate, narrowly scoped. The read vocabulary -- which verb opens which coordinate, what each returns, and the workspace rule -- is in `agent-protocol/read-map.md`. 3. Run the smallest authoritative read-only CLI query for the surfaced domain. Use native output/filter flags and one command per call. 4. Record the query, result, and uncertainty in the contract checkpoint. 5. Deep-dive only where the evidence identifies a gap or inconsistency.
Do not invoke helpers from `.claude/`; that tree is an installed/protected surface, not Gaia source. Do not treat a broad health command's exit code as proof of a specific desired state. If investigation forecasts mutation, switch to `investigation` and collect predictable exact T3 commands before requesting consent.
Generative AI Interface for Agents. Specialist agents for Claude Code and OpenCode, with a memory that outlives the session and a consent gate on everything that changes state.
Other skills on gaia.
More skills from other plugins.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Questions about fast-queries.
- Which coding agents can use fast-queries?
- fast-queries installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.

