task-deliver
Close out a subtask behind a completion gate and mark it complete in progress.md. Run it after the tests pass, before you start the next subtask.
Target: Target not categorized. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original English text
Topics in the source
- task-deliver workflow (v3)
- Overview
- Phase 01 completion gate (R20.10 + D-10 + ADR 0039)
- Parallelism — completion gate 正交 wrapper
- {{ host.team.attributive }} conditional escalation (D-11 + agent-teams.md 5 OR-chain)
- R20.10 explicit maxiterationsexceeded handler (NOT silent abort)
- Phase 02 progress-mark planning-with-files (D-15 + Q-AUDIT-5a Option A)
- How to invoke
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 {{ host.team.wrapped }} 升级 5 触发 OR-chain + R20.10 explicit maxiterationsexceeded handler). | phase | id | upstream | model | capability / args / parallelism / fallback | | ----- | -- | -------- | ----- | ------------------------------------------ | | 1 | 01-deliver | (none — harnessed 自有 CLI) | haiku | {{ capabilities.completion-gate.cmd }} + args: {completionpromise: COMPLETE, maxiterations: ...} + parallelism: judgments.parallelism-gate.completion-gate-wrapper.fires + fallback.maxiterationsexceeded.action: emitwarningandhalt | | 2 | 02-progress-mark | planning-with-files | haiku | {{ capabilities.planning-with-files.cmd }} / invokes: /plan / artifactsexpected: [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+. 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
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- easyinplay/harnessed
- Source file
- workflows/task/deliver/SKILL.md
- Fixed revision
- f272b6e2bcc05793dde6ad7146da602381fe1351
Requirements
- Only the author’s Skill metadata is included. Read the full instructions to check dependencies, licensing and conditions of use.
A small first task
先阅读原作者说明，再决定是否在自己的 AI 工具中使用。
Instructions for your AI tool
- Claude Desktop: resource-specific guide not available yet
- Claude Code: resource-specific guide not available yet
- Cursor: resource-specific guide not available yet
- Codex: resource-specific guide not available yet
Author documentation is not live verification by this site. Without evidence, we do not mark a resource as compatible, safe or free.
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: easyinplay/harnessed · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-10T08:01:58.198Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
Apache-2.0. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.