← ClaudeAtlas

task-deliverlisted

task-deliver workflow v3 — Stage ③.d 子任务交付 sub-workflow (harnessed 自有 completion-gate + Agent Teams conditional escalation + R20.10 explicit max_iterations_exceeded fallback)。2-phase composition: 01-deliver (completion-gate with completion_promise verbatim "COMPLETE" + parallelism judgments.parallelism-gate.completion-gate-wrapper.fires + fallback emit_warning_and_halt exit_code 1) → 02-progress-mark (Claude Code plugin /plan mark subtask complete in progress.md)。 schema_version: harnessed.workflow.v3 with disciplines_applied [6] + tools_available [completion-gate, verification-before-completion, agent-teams-create, agent-teams-send-message, agent-teams-shutdown, planning-with-files]. Triggered by harnessed CLI `harnessed task-deliver --task <text>` or slash command `/task-deliver` after `harnessed setup`.
easyinplay/harnessed · ★ 2 · AI & Automation · score 71
Install: claude install-skill easyinplay/harnessed
# task-deliver workflow (v3) ## Overview 2-phase sub-workflow mapping the user's CLAUDE.md Stage ③.d 子任务交付 discipline onto the harnessed runtime, fully `harnessed.workflow.v3` schema (Phase v3.0-3.4 W0 T3.4.W0.9 — D-09 L0 Discipline Substrate + D-10 completion gate + D-11 Agent Teams 升级 5 触发 OR-chain + R20.10 explicit max_iterations_exceeded handler). | phase | id | upstream | model | capability / args / parallelism / fallback | | ----- | -- | -------- | ----- | ------------------------------------------ | | 1 | `01-deliver` | (none — harnessed 自有 CLI) | haiku | `{{ capabilities.completion-gate.cmd }}` + `args: {completion_promise: COMPLETE, max_iterations: ...}` + `parallelism: judgments.parallelism-gate.completion-gate-wrapper.fires` + `fallback.max_iterations_exceeded.action: emit_warning_and_halt` | | 2 | `02-progress-mark` | planning-with-files | haiku | `{{ capabilities.planning-with-files.cmd }}` / `invokes: /plan` / `artifacts_expected: [progress.md]` | Per-phase config loads from `workflows/task/deliver/workflow.yaml`; engine.runRouting spawns each phase as a sub-agent via `@anthropic-ai/claude-agent-sdk` 0.3.142+. ## Phase 01 completion gate (R20.10 + D-10 + ADR 0039) 完成判据是子任务输出包含 verbatim `"COMPLETE"` string (NOT 启发式 / NOT LLM-as-judge)。 4.36.0 起这条保证**完全内置**,跑在 harnessed 自己的 live path 上,不依赖任何上游 plugin: - `harnessed checkpoint complete <sub> --result-file <path>` — fail-CLOSED,同时校验 声明的 `artifacts_expected` 产物存在、TDD boundary 通过(证据非空 / 红绿两侧齐全 / 测试文件未被删除)、结果