From agent-harness-kit
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.
How this command is triggered — by the user, by Claude, or both
Slash command
/agent-harness-kit:SKILLtemplates/.claude/skills/context-query/This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# Context Query 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. ## Usage Install `srcwalk` for better structural hits: `srcwalk` is recommended, not required by default. Use `--require-srcwalk` when the environment should fail closed if structural search is unavailable. ## Output Contract - `rankedFiles`: highest-confidence files with scores and reasons - `sources`: concise path:line evidence snippets - `nextReads`: foll...
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 notesnpx claudepluginhub tuanle96/agent-harness-kit --plugin agent-harness-kit/SKILLResolves GitHub issue via isolated worktree, TDD workflow, and auto-closing PR creation.
/SKILLCreates conventional git commit from conversation intent using git-agent and pushes to remote. Accepts optional Claude model name for co-author.
/SKILLSurfaces current session task from state file, evaluates clarity (prompts for clarification if needed), assesses completion, and verifies if fully done.