investigate
Delegate read-only investigation, debugging, audit, search, or code-understanding tasks to sub-agents; synthesize only from their structured reports.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Delegate read-only investigation, debugging, audit, search, or code-understanding tasks to sub-agents; synthesize only from their structured reports.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Use when bootstrapping a repository — greenfield or brownfield — into Uhstray's standard development conventions, OpenSpec, and the two-store memory setup. Idempotent and non-destructive: safe to re-run, never overwrites existing docs. Triggers on "repo kickstart", "bootstrap this repo", "set up our conventions", "conform this repo", "initialize plans/openspec/memory", "initialize this repo for openspec and memory", "set up two-store memory here", "index this repo and create its memory bank".
Use when checking or setting up the four-strata memory system on this machine and in the current project — "is my memory set up right", "memory onboarding", "set up memory", "check my memory setup", after a fresh machine/repo, when repo-kickstart or buhhdy's preflight reports memory degradation, or when .claude/memory / MemPalace / evolve looks misconfigured.
Use when any orchestrating agent's development workflow — buhhdy's Workflow 2 is the canonical caller — has open PRs that need driving from creation through merge and cleanup — the terminal step once PRs are open. Triggers on "shepherd this PR", "drive the PR to merge", "babysit the PRs", "monitor the PR to merge", and post-merge close-out (close linked issues, archive the change, remove the worktree, janitor stale branches in the orchestrator's own prefix (buhhdy/* canonical)). Also load to verify PR-lifecycle preconditions (branch protection, CodeRabbit) before shepherding.
Use when the user says "remember", "don't forget", "save that", "keep that in mind", "recall", "what do we know about", "look that up", or any request to persist or retrieve project knowledge — stores memories in .claude/memory/ using the Claude Code memory format, committed to git so the whole team shares context.
Use when starting new planning/research on a project or picking up development against an existing plan — buhhdy's two standard, repeatable sequences: Planning & Research (fresh problem to a validated plan — an OpenSpec change where the repo has adopted the conventions — plus issues) and Development (fanout, audit, docs, and pr-shepherd).
Reference skill for buhhdy's provider routing logic — the decision tree, model tier table, per-provider strengths, skill-to-provider affinity, and cross-review pairings. Load when reasoning about which provider to use and why, or when a task doesn't clearly match the main routing tree.
| name | investigate |
| description | Delegate read-only investigation, debugging, audit, search, or code-understanding tasks to sub-agents; synthesize only from their structured reports. |
Use for any read-only task: investigation, debugging, audit, search, code understanding, architecture comparison, failure analysis, or answering a repository-specific technical question.
claude_code, codex, or a gemini-* worker
(gemini-standard by default; gemini-lite for bulk sweeps; gemini-complex
for multimodal/large-corpus — model is baked into each gemini-* worker,
so never pass args.model to them):
sys_session_send(agent="claude_code"|"codex"|"gemini-standard"|"gemini-lite"|"gemini-complex", title="explore-<task_slug>", args={purpose: "explore", input: "<question + exact scope + evidence requested>"}). Use a task-based title such as
explore-ci-flake, never the raw vendor name. Use purpose: "search" only
when the task is primarily external/document search. Prefer a gemini-*
worker when a third lens or a non-Claude/GPT model is wanted. claude_code and codex take an optional
args.model (sys_list_models shows what each can run; an invalid
model/worker combination fails loud at dispatch, and model only applies on
the dispatch that CREATES the session — a send that continues an existing
title rejects it); NEVER pass args.model to a gemini-* worker — the
model is baked into the worker.
Tell the worker to edit nothing and return file,
command, URL, or line evidence. Emit these sys_session_send calls in the
SAME turn — do not end a turn having only said you will dispatch.sys_read_inbox. Synthesize only from those inbox-delivered reports. Use
sys_session_get_history only to debug an empty or unclear worker result; if
reports conflict or are incomplete, dispatch a follow-up explore task
rather than resolving the conflict from your own direct inspection.fanout /
cross-review: dispatch an implement worker, then verify with the
opposite-vendor review worker.