← ClaudeAtlas

investigationlisted

Use when starting an investigation, analyzing existing code or infrastructure, or building findings before proposing changes
metraton/gaia · ★ 3 · DevOps & Infrastructure · score 76
Install: claude install-skill metraton/gaia
# Investigation Investigate from cheapest authoritative context toward narrowly scoped live evidence. The purpose is both diagnosis and a reliable mutation forecast. ## Evidence ladder 1. Read the injected dispatch kernel -- `# Your Contract` (goal, role, `project`, the `can_read` menu) and `# What I know about you`. Do not re-derive facts it already supplies. 2. Pull what the goal needs from the substrate on demand -- none of it is preloaded, and a coordinate in the goal (a contract id, a memory slug, a brief) is an instruction to go read it. The verbs, their addressing, and the workspace rule that decides whether they resolve are in `agent-protocol/read-map.md`. Do not read Gaia's database directly. 3. Inspect the smallest relevant source files, tests, configuration, git diff, or runtime query. Prefer authoritative implementation over prose. 4. Record each material source immediately in the contract: `files_checked`, `patterns_checked`, `commands_run`, `key_outputs`, exact excerpts in `verbatim_outputs`, whatever your change reaches outside the file you were sent to in `cross_layer_impacts`, and uncertainty in `open_gaps`. When the finding needs a supporting file too large for `verbatim_outputs` (a full command dump, a rendered report), stage it under the canonical Gaia scratch directory (`~/.gaia/scratch`, never the workspace/client repo), named after the current turn's `contract_id` (`<agent_id>.<token>`, bare or with one tr