feat: add complete PR workflow commands and enhance audit system#17
Merged
feat: add complete PR workflow commands and enhance audit system#17
Conversation
Add three new workflow commands to streamline PR creation and review: - /plan: Extract and let user select tasks from discussion - /pull-request: Create PR with auto-generated description - /resolve-comments: Systematically address PR review feedback Also add pull-request sub-agent for comprehensive PR analysis. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Restructure all 9 audit sub-agents to categorize findings into: - 🔴 Issues in your changes (BLOCKING) -⚠️ Issues in code you touched (SHOULD FIX) - ℹ️ Pre-existing issues (INFORMATIONAL) This provides clearer focus on what must be fixed before merge vs. what can be deferred to separate PRs. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Completely rewrite /code-review to: - Orchestrate all audit sub-agents in parallel - Synthesize findings from new three-category reports - Generate actionable summary with clear priorities - Separate blocking issues from informational findings 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Update init.ts to install new workflow commands. Update plan-next-steps to remove unused tool references. Update README.md with documentation for new commands. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
- Fix README CLI examples (devflow → npx devflow-kit) - Add Prerequisites section to /resolve-comments (gh CLI dependency) - Add Edge Cases section to /plan (cancellation, empty selection) - Add Troubleshooting section to /pull-request (error recovery) Addresses critical documentation gaps identified in code review. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This reverts commit 5c6aaea.
Update CLI examples to use correct npx invocation: - devflow init → npx devflow-kit init - devflow uninstall → npx devflow-kit uninstall Package is published as devflow-kit, so users need npx prefix. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Add NodeSystemError interface and type guard function to safely check error.code property instead of using unsafe 'any' type. Changes: - Add isNodeSystemError() type guard function - Replace error: any with error: unknown (2 instances) - Use type guard before accessing error.code property Improves type safety without changing runtime behavior. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
dean0x
pushed a commit
that referenced
this pull request
Mar 14, 2026
Batch 1 — Mechanical fixes: - Fix duplicate step 5→6 in 4 explorer prompts (implement-teams.md) - Fix fractional 2.5→3 renumbering in 4 reviewer prompts (code-review-teams.md) - Fix fractional 1.5→2 renumbering in reviewer.md responsibilities - Update stale counts: 24→31 skills, 8→17 plugins (file-organization.md) - Add missing ambient-prompt.sh to hooks listing (file-organization.md) Batch 2 — DRY extraction via knowledge-persistence skill: - Create shared/skills/knowledge-persistence/SKILL.md with canonical procedure (ADR/PF formats, lock protocol, capacity cap, dedup, TL;DR update) - Replace 8 inline extraction procedures with skill references in implement, code-review, debug, resolve (base + teams variants) - Register skill in 4 plugin manifests (plugin.json + plugins.ts) Batch 3 — Hook improvements: - Collapse head+sed+grep into single sed -n for TL;DR extraction - Guard section joins to prevent leading newlines when Section 1 skipped Batch 4 — Quick fixes: - Add TL;DR-only rationale comment to skimmer.md step 6 - Log createMemoryDir errors in verbose mode instead of silent catch - Add 3 hook integration tests (TL;DR injection, no leading newlines, no knowledge section when files absent) Issues dismissed: #9 (TL;DR sanitization — trust model), #10 (integrity verification — instruction-enforced), #17 (mkdir failure test — low value), #18 (phase ordering cosmetic), #19 (intentional scope exclusion)
dean0x
pushed a commit
that referenced
this pull request
Mar 14, 2026
…eMemoryDir failure test - /specify: Add Phase 2.5 to read decisions.md + pitfalls.md before exploration. Constraints and Failure Modes explorers now receive prior decisions and known pitfalls as context. - /self-review: Phase 0 reads knowledge files. Simplifier and Scrutinizer receive KNOWLEDGE_CONTEXT to check for reintroduced pitfall patterns and verify architectural consistency. - Add createMemoryDir failure test (file blocking mkdir path). Resolves review issues #17 and #19 from PR #140.
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.
Complete PR Workflow Commands and Enhanced Audit System
This PR adds a comprehensive set of workflow commands to streamline the entire pull request lifecycle, from planning to creation to review resolution. It also restructures the audit system to provide clearer, more actionable feedback focused on changes actually made in the PR.
Summary
DevFlow now provides a complete workflow from idea to merged PR:
/plan)/implement)/code-review)/pull-request)/resolve-comments)The audit system has been refactored to categorize findings into three clear priorities: blocking issues in your changes, issues in code you touched, and pre-existing informational issues.
Key Changes
New Workflow Commands
/plan- Interactive Planning with Design Decisions/pull-request- Smart PR Creation--draftflag and custom base branchpull-requestsub-agent for deep analysis/resolve-comments- Systematic Review ResolutionRefactored Audit System
Three-Category Reporting (all 9 audit agents updated):
Enhanced
/code-reviewCommand:Type Safety Improvements
Node.js Error Handling (
src/cli/commands/init.ts):NodeSystemErrorinterface with proper typingisNodeSystemError()type guard functionerror: anywitherror: unknown(2 instances)error.codeproperty with type guardDocumentation Updates
README.md:
Test Plan
New Commands
/planafter a discussion and verify task selection UI/pull-requeston a branch and verify PR creation/resolve-commentson a PR with feedback/code-reviewand verify three-category reportingType Safety
npm run buildand verify no TypeScript errorsnpx devflow-kit initwhen settings.json existsBreaking Changes
None. All changes are additive.
Files Changed
/plan,/pull-request,/resolve-comments(3)pull-request(1)init.tsTotal: 17 files, +3143/-2070 lines
🤖 Generated with Claude Code