ci(classify): widen t2 surface from .claude/scripts/* to .claude/* - #24
Merged
adithya0597 merged 1 commit intoJul 22, 2026
Merged
Conversation
.claude/agents, .claude/skills, and .claude/settings.json define loop behavior (loop-verifier's default-REJECT stance, the triage skill's no-code-edits rule, the Stop hook) but classified as t1 ordinary — a PR flipping the verifier to default-APPROVE would skip the founder-highlights digest. Same risk class as .claude/scripts, so same tier. Verified by extracting the SYNC-REGION and running classify_tier: all tracked .claude paths now emit t2; loops/daily-triage state files stay t0. Note: the local scratchpad/hot/test_classify_tier.sh fixture (not in-repo) may assert t1 for non-script .claude paths and would need its expectation updated. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
Founder highlights — this PR touches t2 (highest-risk) surface. Files that triggered t2:
|
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
.claude/agents/*,.claude/skills/*, and.claude/settings.jsondefine loop behavior — the verifier's default-REJECT stance, the triage skill's no-code-edits rule, and the repo Stop hook — but classified as t1 ordinary. A PR quietly flippingloop-verifier.mdto default-APPROVE would skip the founder-highlights digest. These files are the same risk class as.claude/scripts/*, so they get the same tier.Change
One pattern inside the
classify_tierSYNC-REGION:.claude/scripts/*→.claude/*(plus the matching header-comment mention). Covers scripts, agents, skills, and settings in one glob.Proof
Extracted the SYNC-REGION verbatim and ran
classify_tier:.claude/agents/loop-verifier.md.claude/skills/loop-triage/SKILL.md.claude/settings.json.claude/scripts/foo.shloops/daily-triage/STATE.mdREADME.mdNote for the local fixture
This edits inside the SYNC-REGION, so the local
scratchpad/hot/test_classify_tier.sh(not in-repo; extracts the region verbatim) may assert t1 for non-script.claudepaths — update its expectations when running it next.🤖 Generated with Claude Code