feat: enhance commands with brainstorm/design workflow and issue triage#19
Merged
feat: enhance commands with brainstorm/design workflow and issue triage#19
Conversation
The research agent and command were too heavy-handed for exploratory work. Replace with: - brainstorm agent: explores design decisions and approaches - design agent: creates detailed implementation plans Research skill now delegates to brainstorm agent for pattern discovery. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
New workflow separates concerns: - /brainstorm: explore architectural approaches and trade-offs - /design: create detailed implementation plans with integration points Agents follow project documentation framework with .docs persistence. Commands orchestrate Task tool invocations per orchestration principle. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
…breakdown /plan now provides deliberate triage: - Implement now: add to todos - Defer to GitHub: create and lock issue - Skip entirely: not worth tracking /breakdown: quick task decomposition without interactive triage. Commands use minimal tools (AskUserQuestion, TodoWrite, Bash only) following the orchestration principle - no heavy codebase scanning. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Apply standardized documentation framework across all persisting agents: - Timestamps: YYYY-MM-DD_HHMM (sortable, readable) - Branch slugs: sanitize / to - for file paths - Consistent .docs/ directory structure Streamline /implement command: - Remove interactive triage (use /plan for that) - Focus on efficient task execution with minimal interruption - Only stop for genuine design decisions Update CLAUDE.md with framework documentation. Update README.md with new command descriptions (/plan, /breakdown). Update CLI init.ts with aligned command descriptions. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
The /commit command now executes commits immediately after safety checks pass, without asking for user confirmation. Trust the agent's judgment. Safety checks still abort for: - Secrets, credentials, API keys - Sensitive files (.env, *.key, etc.) - Dangerous patterns But once safe, execute without interruption. 🤖 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.
Summary
Major enhancement of DevFlow commands focusing on structured planning and deliberate decision-making.
Key Changes:
/researchwith focused/brainstorm(exploration) and/design(planning)/planfor deliberate issue triage with GitHub integration/plan-next-stepsto/breakdownfor concise quick captures/commitworkflow - trust the agentChanges
New Workflow
/brainstorm- Explore architectural approaches and trade-offs/design- Create detailed implementation plans with integration points/plan- Triage issues: implement now, defer to GitHub issue, or skip/breakdown- Quick task decomposition (renamed from plan-next-steps)Architectural Improvements
Stats
Test plan
npm run build- passes/brainstormcommand launches brainstorm agent/designcommand launches design agent/plancreates GitHub issues when user defers/breakdownsaves todos without interaction/commitexecutes without asking for confirmationBreaking Changes
/plan-next-stepsrenamed to/breakdown/researchcommand removed (use/brainstorm+/design)/planbehavior completely changed (triage vs selection)🤖 Generated with Claude Code