agent-exploration
FeaturedCoordinate native explorers for explicitly requested multi-area research with scoped written results and an evidence-backed synthesis.
AI & Automation 2,894 stars
189 forks Updated today MIT
Install
Quality Score: 99/100
Stars 20%
Recency 20%
Frontmatter 20%
Documentation 15%
Issue Health 10%
License 10%
Description 5%
Skill Content
# Agent Exploration
Use when explicitly requested for research across independent areas with written results. Use the current harness's native explorers and configured model/effort; an explicit user override wins. Do not invoke an external runtime or create an agent registry for this workflow.
## Scope and dispatch
1. Resolve the question and output path from the request or active task. Ask only for genuinely missing scope; creating the requested directory needs no additional confirmation. Default an unspecified artifact location to `.audits/exploration/<timestamp>/` and state it.
2. Reuse current grounding. Scout only enough to identify independent questions; no tool-call or source-count quota. Choose as many useful slices as capacity and scope justify, up to 8; `--agents` is an upper bound, not a target to pad.
3. Read `references/dispatch-rules.md` and `assets/explorer-prompt.md` once when preparing dispatch. Send each explorer its question, source scope, exact output path, and the scoped-write contract once. Include `assets/analysis-template.md` when a structured artifact is needed; do not duplicate the contract in several embedded documents.
4. Create the output directory, then dispatch independent slices as capacity permits. Prompts need durable copies only for a long/resumable run. Every worker is read-only except for its named analysis file; no commits or unrelated edits.
5. Inspect each completed artifact and its material citations. A failed slice does not invalid...
Details
- Author
- compozy
- Repository
- compozy/compozy
- Created
- 7 months ago
- Last Updated
- today
- Language
- Go
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
AI & Automation Listed
explore
Use when asked to explore the codebase to map structure, symbols, and dependencies. Not for a single file under 50 LOC: read it directly.
40 Updated 1 months ago
OutlineDriven AI & Automation Listed
explore
Deep exploration of codebase, docs, and web for any topic or question
0 Updated 1 months ago
Vleickzs AI & Automation Listed
explore
Deep codebase exploration using parallel subagents. Use when asked to 'explore', 'understand', 'investigate', 'map out', 'how does X work', or 'audit' a part of the codebase.
0 Updated yesterday
arndvs