docs: sync README, AGENTS.md and CHANGELOG for the rubric, success_rate and research - #51
Merged
Merged
Conversation
…te and research
Doc-sync is enforced in this repo (CHANGELOG + a human doc + an agent guide per
behaviour change) but the pre-push guard is per-clone and was not installed here, so
three merged PRs shipped feature code without it. Paying that debt in one place:
README.md the rubric + how to run it, the 23/23-was-the-bug story with the
archived reproduction, success_rate's two honesty choices, the
attention-budget measurement, project structure, and a test badge
that had been stale at 315 since long before this work (now 606)
AGENTS.md two new component rows (docs/rubrics + scripts/audit_loop_rubric.py,
research/attention-budget) and success_rate on the memory row
CHANGELOG all three additions under [Unreleased]
No behaviour change; documentation only.
Co-Authored-By: Claude Opus 5 (1M context) <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Doc-sync is enforced in this repo — a behaviour change must ship with a CHANGELOG entry, a human doc, and an agent guide — but the
pre-pushguard is per-clone and was not installed here, so PRs #48, #49 and #50 shipped feature code without it. Paying that debt in one place.success_rate()'s two honesty choices; the attention-budget measurement; project structure. Also fixes a test badge stale at 315 since long before this work (now 606).docs/rubrics/+scripts/audit_loop_rubric.py,research/attention-budget/) andsuccess_rateon the memory row.[Unreleased].No behaviour change; documentation only. 606 tests pass.
🤖 Generated with Claude Code