Skip to content

feat(feature): read ERRORS.md in Phase 0 before coding#3604

Merged
PierreBrisorgueil merged 1 commit into
masterfrom
fix/feature-read-errors-md
May 5, 2026
Merged

feat(feature): read ERRORS.md in Phase 0 before coding#3604
PierreBrisorgueil merged 1 commit into
masterfrom
fix/feature-read-errors-md

Conversation

@PierreBrisorgueil

Copy link
Copy Markdown
Contributor

Summary

  • Adds a bullet to Phase 0 step 1 of the /feature skill to read ERRORS.md before coding
  • Ensures known bugs and non-obvious pitfalls are surfaced at the earliest possible point in the feature implementation flow

Changes

Additive only — inserts one bullet under ### 1. Identify target module in .claude/skills/feature/SKILL.md. No existing behaviour is removed or altered.

Closes #3594.

Test plan

  • Confirm the new bullet appears first under Phase 0 step 1 in the skill
  • Backwards compatible: no existing skill step removed or reordered

Adds a bullet in Phase 0 step 1 to read ERRORS.md for known bugs and
non-obvious pitfalls before starting implementation. Closes #3594.
Copilot AI review requested due to automatic review settings May 5, 2026 10:04
@coderabbitai

coderabbitai Bot commented May 5, 2026

Copy link
Copy Markdown

Warning

Rate limit exceeded

@PierreBrisorgueil has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 59 minutes and 50 seconds before requesting another review.

To keep reviews running without waiting, you can enable usage-based add-on for your organization. This allows additional reviews beyond the hourly cap. Account admins can enable it under billing.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 105a13dc-10b5-4c49-be19-260815744d76

📥 Commits

Reviewing files that changed from the base of the PR and between f51e40a and 3d144b7.

📒 Files selected for processing (1)
  • .claude/skills/feature/SKILL.md
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch fix/feature-read-errors-md

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.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@codacy-production

Copy link
Copy Markdown

Up to standards ✅

🟢 Issues 0 issues

Results:
0 new issues

View in Codacy

AI Reviewer: first review requested successfully. AI can make mistakes. Always validate suggestions.

Run reviewer

TIP This summary will be updated as you push new changes.

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates the /feature skill’s Phase 0 (scope analysis) to explicitly read ERRORS.md before any coding, surfacing known pitfalls earlier in the feature implementation workflow.

Changes:

  • Adds a new first bullet under “Phase 0 — 1. Identify target module” instructing to read ERRORS.md before coding.

@PierreBrisorgueil
PierreBrisorgueil merged commit 514fbae into master May 5, 2026
7 checks passed
@PierreBrisorgueil
PierreBrisorgueil deleted the fix/feature-read-errors-md branch May 5, 2026 10:06

@codacy-production codacy-production Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

The PR successfully introduces a mandatory step to check for known pitfalls in ERRORS.md. Codacy analysis shows the code is up to standards with no new quality issues. However, there is a conflict between the requested acceptance criteria (placing the instruction in Phase 0, Step 1) and logical best practices. Placing the check in Step 3 ('Analyze flows & edge cases') is more appropriate for pitfall analysis. Furthermore, the instruction lacks a conditional existence check, which could cause agents to error out if the file is not present in a repository.

About this PR

  • The requirement to read ERRORS.md is currently targeted for the very beginning of Phase 0. While this ensures it isn't missed, it breaks the flow of 'Identify target module'. Consider if this instruction serves the user better during the edge-case analysis phase.

Test suggestions

  • Verify the 'Read ERRORS.md' instruction is present as the first bullet under the 'Identify target module' section
  • Confirm that existing steps regarding module selection and scaffold-running remain intact and in their original relative order
Prompt proposal for missing tests
Consider implementing these tests if applicable:
1. Verify the 'Read ERRORS.md' instruction is present as the first bullet under the 'Identify target module' section
2. Confirm that existing steps regarding module selection and scaffold-running remain intact and in their original relative order

TIP Improve review quality by adding custom instructions
TIP How was this review? Give us feedback


### 1. Identify target module

- Read `ERRORS.md` for known bugs and non-obvious pitfalls to avoid before coding.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚪ LOW RISK

Suggestion: This instruction relates to implementation pitfalls rather than module selection, making its placement under 'Identify target module' inconsistent. Additionally, the command should be conditional to ensure the agent does not halt if the file is absent. Try running the following prompt in your coding agent: > Relocate the ERRORS.md check to '3. Analyze flows & edge cases' and rephrase it as: '- If ERRORS.md exists, read it for known bugs and non-obvious pitfalls to avoid before coding.'

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

feat(feature): read ERRORS.md in Phase 0 before coding

2 participants