Reframe README positioning around the official Claude Code loop taxonomy#17
Merged
Conversation
The comparison section now leads with the official four-type taxonomy (turn-based / goal-based / time-based / proactive) and maps what each type hands off (check, stop condition, trigger, whole prompt) onto the Looper artifact that supplies it. Adds /schedule and routines to the scheduling discussion and table, adds a looper lint row, and corrects the /goal critique to match the documented evaluator-model behavior (single-vendor evaluation rather than literal self-grading). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Tier 1 docs/positioning pass prompted by the Claude Code team's "Getting started with loops" guide.
/goal-vs-/loopsection now leads with the official taxonomy — turn-based / goal-based / time-based / proactive — organized by what each loop type hands off (the check, the stop condition, the trigger, the whole prompt), and shows which Looper artifact supplies each hand-off./scheduleand routines join the scheduling discussion and the comparison table (they were absent).looper lintrow in the table (static design checks are now a real differentiator)./goal's stop condition is checked by an evaluator model per the official docs, so the "same model grading its own homework" claim is softened to what is actually true — single-vendor evaluation with no typed rubric and no model-family choice.Docs only; no code paths touched. 41/41 tests green locally.
🤖 Generated with Claude Code