Add development discipline plugin#18
Conversation
|
Warning Review limit reached
Next review available in: 53 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughAdds a new ChangesDevelopment-discipline plugin addition
Estimated code review effort: 2 (Simple) | ~15 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
@coderabbitai re-review |
Rate Limit Exceeded
|
|
@coderabbitai review |
Rate Limit Exceeded
|
|
@coderabbitai re-review |
|
✅ Action performedReview finished.
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (2)
evals/fixtures/behavior/full-marketplace/cases.json (1)
349-375: 🎯 Functional Correctness | 🔵 Trivial | ⚡ Quick winSafety-critical case lacks a deterministic hard guard.
development-discipline-verification-claim-scopeusesvalueGate.mode: "safety-critical"withminPassRate: 1, same asdevelopment-discipline-tdd-one-test-first, but unlike that case it ships withhardAssertions: []. Relying purely onsemanticRubricfor a zero-tolerance gate reintroduces the LLM-rubric flakiness that the hard-guard pattern is meant to prevent for safety-critical cases.Consider adding a
forbiddenIntent(or similar) hard assertion targeting phrases like "the repo is ready" / "whole repo is ready" combined with no re-verification language, mirroring the pattern used for the TDD case.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@evals/fixtures/behavior/full-marketplace/cases.json` around lines 349 - 375, The safety-critical case `development-discipline-verification-claim-scope` currently depends only on the semantic rubric and has no deterministic hard guard. Add a hard assertion in `hardAssertions` (for example a `forbiddenIntent`-style rule) that rejects whole-repo readiness claims like “the repo is ready” or “whole repo is ready” unless paired with fresh re-verification language, using the same hard-guard pattern as the TDD case.scripts/tests/development-discipline-plugin.bats (1)
40-45: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueForward reference:
failis defined beforefailuresexists.
fail()(lines 40-42) closes overfailures, butfailuresisn't declared until line 44. This works only because no call tofail()occurs before line 44 executes — functionally safe here, but fragile to future edits that might callfail()earlier in the script.♻️ Proposed reordering
-function fail(message) { - failures.push(message); -} - -const failures = []; +const failures = []; +function fail(message) { + failures.push(message); +}🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@scripts/tests/development-discipline-plugin.bats` around lines 40 - 45, Move the shared state declaration so it exists before the helper uses it: in the test script, declare `failures` before `fail(message)` or otherwise ensure `fail()` does not close over an as-yet-undeclared variable. Keep `fail()` and `failures` together near the top of the file so future calls to `fail()` cannot hit a forward reference.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@scripts/tests/development-discipline-plugin.bats`:
- Around line 29-34: The requiredCases list in
development-discipline-plugin.bats is missing the systematic-debugging behavior
fixture, so the test does not validate all added cases. Update the requiredCases
array to include development-discipline-systematic-debugging-root-cause so it
matches the full set of skills checked by requiredSkills and covers every
fixture used in the behavior cases JSON.
---
Nitpick comments:
In `@evals/fixtures/behavior/full-marketplace/cases.json`:
- Around line 349-375: The safety-critical case
`development-discipline-verification-claim-scope` currently depends only on the
semantic rubric and has no deterministic hard guard. Add a hard assertion in
`hardAssertions` (for example a `forbiddenIntent`-style rule) that rejects
whole-repo readiness claims like “the repo is ready” or “whole repo is ready”
unless paired with fresh re-verification language, using the same hard-guard
pattern as the TDD case.
In `@scripts/tests/development-discipline-plugin.bats`:
- Around line 40-45: Move the shared state declaration so it exists before the
helper uses it: in the test script, declare `failures` before `fail(message)` or
otherwise ensure `fail()` does not close over an as-yet-undeclared variable.
Keep `fail()` and `failures` together near the top of the file so future calls
to `fail()` cannot hit a forward reference.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: bd84995c-bfd6-49c1-926b-d0da48a20f6d
📒 Files selected for processing (14)
.agents/plugins/marketplace.json.claude-plugin/marketplace.jsonREADME.mdevals/fixtures/behavior/full-marketplace/cases.jsonplugins/development-discipline/.claude-plugin/plugin.jsonplugins/development-discipline/.codex-plugin/plugin.jsonplugins/development-discipline/README.mdplugins/development-discipline/skills/receiving-code-review/SKILL.mdplugins/development-discipline/skills/systematic-debugging/SKILL.mdplugins/development-discipline/skills/test-driven-development/SKILL.mdplugins/development-discipline/skills/verification-before-completion/SKILL.mdplugins/development-discipline/skills/writing-skills/SKILL.mdscripts/tests/development-discipline-plugin.batsscripts/tests/evals-config.bats
|
/trunk merge |
1 participant
Summary
Validation
Provider-backed live evals and real plugin-eval benchmark runs were not run; no tailored benchmark verifier was specified.
Summary by CodeRabbit
New Features
development-disciplineplugin to the marketplace, with support across the available tool catalogs.Tests