fable-loop

1# The Fable Loop
2 
3This skill orchestrates the fable-method: read its SKILL.md first; its rules govern every stage. It is installed alongside this skill (in this plugin's `skills/fable-method/` directory, or `~/.claude/skills/fable-method/` for manual installs). The method says WHAT to check; this loop says WHO does the work: what runs in the main thread, what fans out to subagents, and what gets attacked before delivery.
4 
5**Gate first.** Trivial per the method's triviality gate: just do it, verify with the one obvious check, report in two sentences. No stages, no subagents. Everything else runs the four stages below in order.
6 
7## Stage 1 - PLAN (the first bookend)
8 
91. Apply method Steps 0-3: classify the ask, define done with a named verification, state load-bearing assumptions.
102. **Evidence fan-out.** Spawn the evidence gatherers as parallel subagents in ONE message, never sequentially:
11   - codebase questions: an Explore agent per distinct area ("how does X work", "what depends on Y");
12   - library or fact questions: a research agent that fetches current docs or searches the web;
13   - each subagent returns distilled findings with citations, never raw file dumps.
14   One batch plus one follow-up batch is the budget; a third needs a stated reason.
15…