agent-comms
SendMessage recipient validation and worktreePath safety (CWE-59). TRIGGER when: validating a SendMessage `to:` recipient against the agent whitelist, or a…
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).
$ npx -y skills add komluk/scaffolding --skill planning-methodology --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/planning-methodologyContext preview
The summary Claude sees to decide when to auto-load this skill.
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).
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)."
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, 36 skills, 19 commands, 15 hooks, per-phase model tiers, opt-in lifecycle hooks, optional cross-device semantic memory.
Repo: komluk/scaffolding
SendMessage recipient validation and worktreePath safety (CWE-59). TRIGGER when: validating a SendMessage `to:` recipient against the agent whitelist, or a…
3-tier markdown memory protocol (shared/agent/conversation) for cross-session knowledge. TRIGGER when: reading or writing agent memory files, choosing which…
RESTful API design standards: resource naming, HTTP methods, status codes, pagination, versioning. TRIGGER when: designing new API endpoints, defining error…
Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets…
Schema design, index strategy, migration safety, and query analysis. TRIGGER when: designing tables or indexes, writing a migration, or diagnosing a slow…