← ClaudeAtlas

light-researchlisted

Light research over a large scope (auditing a whole repository, rereading many documents) at reduced token cost, by splitting the work into batches read by Haiku subagents. Use when a request is vague ("audit all the code", "read all the documents") and the scope exceeds about 30 files or 50,000 estimated tokens.
titouannwtt/claude-tools · ★ 1 · AI & Automation · score 74
Install: claude install-skill titouannwtt/claude-tools
# light-research Objective: reduce the token cost of a vague task over a large scope. The splitting is done by a deterministic script (zero model tokens). Haiku subagents read the batches. Opus writes the synthesis, on the findings only, never on the sources. ## Procedure 1. **Judge the prompt.** Precise (explicit steps and deliverable): do not use this skill. Vague (open scope): continue. 2. **Ask before acting.** Write: "Do you want light research by Haiku subagents to reduce tokens?" - No: handle the request as best you can, without batches. - Yes: continue. 3. **Measure the scope.** Run `python3 ~/.claude/skills/light-research/scripts/plan_batches.py <folder> --budget 25000`. The JSON gives the number of files, the estimated tokens and the batches. If the scope is under 30 files and 50,000 tokens, do it yourself: do not launch subagents. 4. **Specify the question.** One sentence: what you are looking for in each batch (bugs, debt, inconsistencies, security...). Without a precise question, the findings will be vague. 5. **Launch the batches.** One `researcher` subagent (Haiku 5.5, medium) per batch, all in **a single message** (at most 10 at a time). Each brief contains: objective, exact list of the batch's files, question, output file (`<scratchpad>/lot-<id>.json`), output schema, stop condition. See the template below. 6. **Synthesize.** One `analyst` subagent (Opus 5.5, medium) reads only the findings files, deduplicates them, ranks them