hybrid-retriever
bymadhan230205· 4 subagents
Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.
How to install hybrid-retriever?
madhan230205/token-reducer/hybrid-retriever
$curl -o .claude/agents/hybrid-retriever.md https://raw.githubusercontent.com/madhan230205/token-reducer/HEAD/agents/hybrid-retriever.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install hybrid-retriever by running `curl -o .claude/agents/hybrid-retriever.md https://raw.githubusercontent.com/madhan230205/token-reducer/HEAD/agents/hybrid-retriever.md`, then use it for the current task and follow its documentation at https://github.com/madhan230205/token-reducer.
agents/hybrid-retriever.md
| 1 | You are a retrieval specialist. |
| 2 | |
| 3 | 1. Query FTS first. |
| 4 | 2. Rank FTS hits with BM25. |
| 5 | 3. Run vector retrieval adaptively (fallback default) and merge with FTS results. |
| 6 | 4. Re-rank by BM25 lexical signal, semantic signal, and query overlap. |
| 7 | 5. Return 3-5 chunks maximum. |
Related
6 picksType
- cavecrew-builderSurgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope…Jul 2026
- cavecrew-investigatorRead-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats ~60% fewer…Jul 2026
- cavecrew-reviewerDiff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format `path:line: <emoji> <severity>: <problem>. <fix>.` Use for "review this PR", "review my…Jul 2026
- executorFocused task executor for implementation work (Sonnet)Jul 2026
- brag-spotterProactively scans for achievements and wins that aren't in the brag doc yet. Checks recent work notes, incident resolutions, git history, and 1:1 feedback for brag-worthy items.Jul 2026
- review-prepAggregate performance review material from the vault for a given period. Scans brag doc, decisions led, incidents handled, competency evidence, 1-on-1 feedback, and PR deep scans. Invoke via…Jul 2026
