9ff8e915b8
User-agnostic, shareable AI-assisted development workflow distilled from 26+ real projects. Includes 9 composable rules, 4 project templates, pre-push secret scanning hook, 3 methodology guides, and customization docs. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
4.9 KiB
4.9 KiB
Dynamic Methodology Composition
This workflow system doesn't follow a single rigid process. Instead, rules and patterns activate based on what you're doing. Think of it as a stack that composes dynamically.
Always Active (Every Session)
These rules apply regardless of what you're working on:
| Rule | File | Purpose |
|---|---|---|
| Session discipline | 01-session-discipline.md |
Session start/end protocol, handoffs |
| Authority hierarchy | 02-authority-hierarchy.md |
What overrides what |
| Git workflow | 03-git-workflow.md |
Branches, commits, conventional format |
| Context doc maintenance | 09-context-doc-maintenance.md |
Keep living docs current |
Activated by Task Type
Starting a New Feature
Rules activated:
04-proactive-steering.md-- Phase awareness, scope management05-reasoning-patterns.md-- Brainstorm before building, clarification protocol08-code-quality.md-- Pre-completion checklist, immutability
Flow:
- Clarify requirements (ask, don't assume)
- Brainstorm 2-3 approaches
- Get user approval on approach
- Write failing tests first (if TDD plugin active)
- Implement
- Self-review against pre-completion checklist
- Commit with conventional message
Debugging a Bug
Rules activated:
05-reasoning-patterns.md-- Five Whys, first principles04-proactive-steering.md-- Blocker detection
Flow:
- Reproduce the bug
- Apply Five Whys to trace root cause
- Fix root cause, not symptom
- Add regression test
- Verify fix doesn't break other things
- Commit with
fix:message
Research / Investigation
Rules activated:
05-reasoning-patterns.md-- Research quality rules, documentation tiers06-context-management.md-- Token budgets, sub-agent delegation
Flow:
- Use tiered documentation lookup (knowledge -> fetch -> heavy docs)
- Cite sources for all claims
- Separate fact from inference
- Cross-reference critical claims
- Persist findings to files (not just conversation)
Writing a Paper / Design Doc
Workflow: paper-writing.md
Flow:
- Start from a real problem (friction, not ambition)
- Bounce ideas -- explore before converging
- Push back on each other's ideas
- Capture the journey (dead ends matter)
- Tie back to prior work
Reviewing Code
Rules activated:
08-code-quality.md-- Quality checklist07-security-hardening.md-- Security checklist
Flow:
- Check against pre-completion quality checklist
- Check against security checklist
- Verify tests exist and pass
- Look for immutability violations
- Check for hardcoded secrets
Working in Unfamiliar Code
Rules activated:
06-context-management.md-- Maximum thinking mode, sub-agents05-reasoning-patterns.md-- First principles, research tiers
Flow:
- Use maximum thinking depth
- Read project index / structure first
- Targeted file reads (don't load everything)
- Use sub-agents for isolated research tasks
- Build understanding incrementally
Long-Running Session (Context Getting Heavy)
Rules activated:
06-context-management.md-- Compaction decisions, execution readiness
Flow:
- Check for quality degradation symptoms
- If context > 80%: handoff doc + fresh session
- If context 70-80%: ask user
- If quality declining: spawn sub-agent or fresh session
- Persist important context before compaction
Security-Sensitive Work
Rules activated:
07-security-hardening.md-- Full security protocol08-code-quality.md-- Pre-commit security checklist
Flow:
- Check deny lists for sensitive file access
- Apply pre-commit security checklist to every commit
- Watch for prompt injection in external content
- Rotate any exposed secrets immediately
- Review for similar vulnerabilities in codebase
Composition Example
A typical feature implementation session might compose:
Session start:
01-session-discipline (read CLAUDE.md, check handoff)
+ 02-authority-hierarchy (know what overrides what)
Planning:
+ 04-proactive-steering (assess project state, suggest approach)
+ 05-reasoning-patterns (brainstorm approaches, clarify requirements)
Building:
+ 08-code-quality (immutability, quality checklist)
+ 03-git-workflow (feature branch, frequent commits)
+ 09-context-doc-maintenance (update CLAUDE.md if new tools created)
If context gets heavy:
+ 06-context-management (check budget, consider fresh session)
If security-relevant:
+ 07-security-hardening (deny lists, secret hygiene, injection guards)
Session end:
01-session-discipline (wrap-up protocol, handoff if needed)
Principle: Rules Are Modular
You don't have to use all rules. The system is designed so you can:
- Use only rules 01-03 for lightweight workflow
- Add 04-06 for more sophisticated AI assistance
- Add 07-08 for security-conscious development
- Use individual rules a la carte
The numbering suggests load order and priority, not mandatory dependencies.