一键导入
pre-phase-briefing
Full execution protocol for MODE: PRE-PHASE BRIEFING -- phase-start context assembly, evidence review, and task readiness checks.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Full execution protocol for MODE: PRE-PHASE BRIEFING -- phase-start context assembly, evidence review, and task readiness checks.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | pre-phase-briefing |
| description | Full execution protocol for MODE: PRE-PHASE BRIEFING -- phase-start context assembly, evidence review, and task readiness checks. |
This protocol is loaded on demand by the architect stub in src/agents/architect.ts. The architect prompt keeps only activation, action, and hard safety constraints; the full execution details live here.
Before creating or resuming any plan, you MUST read the previous phase's retrospective.
Phase 2+ (continuing a multi-phase project):
.swarm/evidence/retro-{N-1}/evidence.json for the previous phase's retrospectivelessons_learned and top_rejection_reasons→ BRIEFING: Read Phase {N-1} retrospective.
Key lessons: {list 1-3 most relevant lessons}
Applying to Phase {N}: {one sentence on how you'll apply them}
Phase 1 (starting any new project):
.swarm/evidence/ for any retro-* bundles from prior projectsuser_directives — these carry across projects→ BRIEFING: Reviewed {N} historical retrospectives from this workspace.
Relevant lessons: {list applicable lessons}
User directives carried forward: {list any persistent directives}
OR if no historical retros exist:
→ BRIEFING: No historical retrospectives found. Starting fresh.
This briefing is a HARD REQUIREMENT for ALL phases. Skipping it is a process violation.
Before any spec generation, plan creation, or plan ingestion begins, the Architect must dispatch the Explorer agent in targeted, scoped chunks — one per logical area of the codebase referenced by the work (e.g., per module, per hook, per config surface). Each chunk must be explored with full depth rather than a broad surface pass.
For each scoped chunk, Explorer must determine:
Explorer outputs a CODEBASE REALITY REPORT before any other agent proceeds. The report must list every referenced item with one of: NOT STARTED | PARTIALLY DONE | ALREADY COMPLETE | ASSUMPTION INCORRECT
Format: REALITY CHECK: [N] references verified, [M] discrepancies found. ✓ src/hooks/incremental-verify.ts — exists, line 69 confirmed Bun.spawn ✗ src/services/status-service.ts — ASSUMPTION INCORRECT: compactionCount is no longer hardcoded (fixed in v6.29.1) ✓ src/config/evidence-schema.ts:107 — confirmed phase_number min(0)
No implementation agent (coder, reviewer, test-engineer) may begin until this report is finalized.
This check fires automatically in:
GREENFIELD EXEMPTION: If the work is purely greenfield (new project, no existing codebase references), skip this check.
Apply when implementing features, fixing bugs, debugging errors, investigating failures, tracing root causes, reviewing tech debt, tracing issues, planning fixes, or completing any task. Enforces parallel sub-agent implementation, independent adversarial review, and a 95% confidence gate before stopping.
RAGAPPv3 testing policy and conventions. Load before writing or modifying any test, fixing a test/CI failure, or adding coverage. Covers backend pytest + unittest (SimpleConnectionPool dependency-override harness, FK cascades, the Python 3.11-vs-local event-loop trap) and frontend Vitest + React Testing Library + jsdom (MemoryRouter, Radix Select, react-virtual mock patterns). This repo's frontend uses Vitest, NOT bun:test.
Keep dependency and lockfile changes aligned with CI expectations.
Verify all required QA gate artifacts and completion criteria before marking a task or phase complete.
Keep mocks, async setup, and test assertions clean and aligned with the code under test.
Lightweight PR-time audit for whether changes are compatible with the actual RAGAPPv3 GitHub Actions workflow, dependency lockfiles, scripts, and cross-platform local validation.