agent-comms
SendMessage recipient validation and worktreePath safety (CWE-59). TRIGGER when: validating a SendMessage `to:` recipient against…
Build minimal, reversible implementation plans. TRIGGER when: turning research into a plan, or sequencing work before writing code. SKIP: gathering documentation (use research-methodology); writing OpenSpec design.md/tasks.md (use spec-design); should this exist at all (use
Claude Code
$ npx -y skills add komluk/scaffolding --skill planning-methodology --agent claude-code
Codex
$ npx skills add komluk/scaffolding --skill planning-methodology -a codex -y
Cursor
$ npx skills add komluk/scaffolding --skill planning-methodology -a cursor -y
Gemini CLI
$ npx skills add komluk/scaffolding --skill planning-methodology -a gemini-cli -y
GitHub Copilot
$ npx skills add komluk/scaffolding --skill planning-methodology -a github-copilot -y
OpenCode
$ npx skills add komluk/scaffolding --skill planning-methodology -a opencode -y
Windsurf
$ npx skills add komluk/scaffolding --skill planning-methodology -a windsurf -y
name: planning-methodology description: "Build minimal, reversible implementation plans. TRIGGER when: turning research into a plan, or sequencing work before writing code. SKIP: gathering documentation (use research-methodology); writing OpenSpec design.md/tasks.md (use spec-design); should this exist at all (use necessity-first)."
Systematic approach for creating minimal, reversible implementation plans after research phase.
## ImplementationPlan: [Feature] ### Scope - Files to modify: X - New files: Y - Tests to add: Z ### Changes | # | File | Action | Verification | |---|------|--------|--------------| | 1 | path/file.ts | MODIFY | type-check | | 2 | path/new.ts | CREATE | builds | ### Steps 1. [Step with verification] 2. [Step with verification] ### Rollback [How to revert each change] ### Success Criteria - [ ] npm run validate passes - [ ] Feature works as specified
> Note: the Plan >= 85 gate is owned by architect/analyst, which run on the opus > tier (`model: opus`, `effort: high`) for higher reasoning rigor. See > `docs/model-tiers.md`.
Plan must score >= 85:
| Criterion | Points | |-----------|--------| | All files listed | 15 | | Step-by-step sequence | 15 | | Verification per step | 15 | | Rollback complete | 15 | | APIs match research | 15 | | Risk assessment | 10 | | Test plan | 10 | | Success criteria | 5 |
Spec-driven multi-agent orchestration for Claude Code — pure markdown, zero backend, runs on the stock runtime. 13 agents, 39 skills, 21 commands, 20 hooks, per-phase model tiers, opt-in lifecycle hooks, optional cross-device semantic memory.
SendMessage recipient validation and worktreePath safety (CWE-59). TRIGGER when: validating a SendMessage `to:` recipient against…
Repo-local file memory under .scaffolding/ (shared/agent/conversation tiers). TRIGGER when: reading or writing .scaffolding/…
RESTful API design standards: resource naming, HTTP methods, status codes, pagination, versioning. TRIGGER when: designing new…
Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an…
Schema design, index strategy, migration safety, and query analysis. TRIGGER when: designing tables or indexes, writing a…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.