一键导入
legion-oracle
Research institutional knowledge before escalating questions to users. Check docs/solutions/ and codebase patterns before asking humans.
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
Research institutional knowledge before escalating questions to users. Check docs/solutions/ and codebase patterns before asking humans.
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。
基于 SOC 职业分类
Use when subscribing sessions to Envoy topics, sending agent-to-agent messages, or reasoning about topic formats for Slack/GitHub/agent routing.
Use when coordinating Legion workers across issues, dispatching workers, monitoring progress, or routing triage items
Use when dispatched by Legion controller to work on an issue in a jj workspace
OpenCode serve HTTP API reference. Use when interacting with sessions, reading messages/todos, aborting workers, managing workspaces, or any direct OpenCode serve API call. Each `opencode serve` process is independent with its own port; Legion runs one shared serve per daemon (default port 13381, may differ if multiple daemons coexist on the host).
Capture learnings from completed work via dual-perspective retrospective. Invoked by resuming an implement worker session — the implementer has full context, and a fresh subagent provides an outside view.
Manage GitHub issues via Projects V2. Use when LEGION_ISSUE_BACKEND=github.
| name | legion-oracle |
| description | Research institutional knowledge before escalating questions to users. Check docs/solutions/ and codebase patterns before asking humans. |
Research institutional knowledge before escalating questions to users.
Check docs/solutions/ first. This codebase captures learnings from past work.
digraph oracle_decision {
"About to ask user a question?" [shape=diamond];
"Is it a preference/requirement?" [shape=diamond];
"Might be documented?" [shape=diamond];
"Ask user directly" [shape=box];
"Use oracle" [shape=box];
"About to ask user a question?" -> "Is it a preference/requirement?" [label="yes"];
"About to ask user a question?" -> "Ask user directly" [label="no - not asking"];
"Is it a preference/requirement?" -> "Ask user directly" [label="yes"];
"Is it a preference/requirement?" -> "Might be documented?" [label="no"];
"Might be documented?" -> "Use oracle" [label="yes"];
"Might be documented?" -> "Ask user directly" [label="no"];
}
Use oracle for: patterns, conventions, solved problems, technical approaches
Ask directly for: preferences, requirements, scope decisions, human judgment
Run steps 1-2 first (parallel OK), then 3-4 if needed:
| Step | Tool | Query |
|---|---|---|
| 1. Institutional learnings | Task learnings-researcher | Search docs/solutions/ for [question] |
| 2. Codebase patterns | Task Explore | Find how src/ handles [topic] |
| 3. Framework docs | Context7 MCP | resolve-library-id → query-docs |
| 4. External practices | Task best-practices-researcher or WebSearch | Current best practices for [topic] |
Found: Answer with source (file:line or URL)
Not found: "Checked docs/solutions/ and codebase - no relevant learnings found" → search externally OR escalate to user
/legion-oracle How should I handle GraphQL pagination?
[learnings-researcher] → No matches
[Explore] → Found src/legion/state/fetch.py uses cursor-based pagination
Answer: Use cursor-based pagination per src/legion/state/fetch.py:42