菜单
Build a compact read-only context packet for a natural-language codebase question. Use before editing unfamiliar code, when tracing task evidence, contracts, validation, or proof paths, or when the relevant files are not obvious.
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
Build a lightweight skill index and load full skill instructions only on demand to reduce startup context pressure.
Select and run a multi-agent workflow pattern for work that exceeds one agent's reliable scope. Use for parallel research, independent reviews, cross-domain changes, or high-risk implementation planning.
Select and run a multi-agent workflow pattern for work that exceeds one agent's reliable scope. Use for parallel research, independent reviews, cross-domain changes, or high-risk implementation planning.
Use composable middleware behaviors for provider/tool execution: retry, caching, timeout, telemetry, and budget guards.
Use this skill whenever the agent makes a mistake, the user observes an avoidable failure, a pattern recurs, or someone says "the agent keeps doing X". Files an "Engineer the Harness" entry — Mitchell Hashimoto's discipline: every failure becomes a permanent prevention mechanism. Always invoke this instead of just fixing the immediate symptom.
Use composable middleware behaviors for provider/tool execution: retry, caching, timeout, telemetry, and budget guards.
| name | context-query |
| description | Build a compact read-only context packet for a natural-language codebase question. Use before editing unfamiliar code, when tracing task evidence, contracts, validation, or proof paths, or when the relevant files are not obvious. |
| allowed-tools | Read, Bash(node .harness/scripts/context-query.mjs:*) |
| suggested-turns | 3 |
Ask the local codebase a natural-language question and get a source-linked read plan. The command is read-only and returns concise ranked files, snippets, and next reads; it does not claim to be a final answer.
node .harness/scripts/context-query.mjs "How does task evidence validation work?" --scope scripts --lane normal --json
node .harness/scripts/context-query.mjs "Where is proof checked?" --scope . --limit 6
Install srcwalk for better structural hits:
npm install -g srcwalk
srcwalk is recommended, not required by default. Use --require-srcwalk
when the environment should fail closed if structural search is unavailable.
rankedFiles: highest-confidence files with scores and reasonssources: concise path:line evidence snippetsnextReads: follow-up files to inspect before editingwarnings: missing optional tools or empty-result notes