# Send Subagent Driven Development to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "subagent-driven-development-2", "name": "Subagent Driven Development", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/wpank/subagent-driven-development-2", "canonicalUrl": "https://clawhub.ai/wpank/subagent-driven-development-2", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/subagent-driven-development-2", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=subagent-driven-development-2", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "subagent-driven-development-2", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T08:43:20.520Z", "expiresAt": "2026-05-08T08:43:20.520Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=subagent-driven-development-2", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=subagent-driven-development-2", "contentDisposition": "attachment; filename=\"subagent-driven-development-2-0.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "subagent-driven-development-2" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/subagent-driven-development-2" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/subagent-driven-development-2", "downloadUrl": "https://openagent3.xyz/downloads/subagent-driven-development-2", "agentUrl": "https://openagent3.xyz/skills/subagent-driven-development-2/agent", "manifestUrl": "https://openagent3.xyz/skills/subagent-driven-development-2/agent.json", "briefUrl": "https://openagent3.xyz/skills/subagent-driven-development-2/agent.md" } } ``` ## Documentation ### Subagent-Driven Development Execute a plan by dispatching a fresh subagent per task, with two-stage review after each — spec compliance first, then code quality. Core principle: Fresh subagent per task + two-stage review = no context pollution, high quality, fast iteration. ### OpenClaw / Moltbot / Clawbot npx clawhub@latest install subagent-driven-development ### When to Use This Skill You have an implementation plan with discrete, mostly independent tasks You want to execute the plan within a single session (no human-in-the-loop between tasks) Tasks can be implemented and reviewed sequentially without tight coupling ConditionThis SkillAlternativeHave a plan, same sessionYes—Have a plan, parallel sessionNoexecuting-plansNo plan yetNoWrite a plan firstTasks tightly coupledNoManual execution or decompose more ### The Process ┌─────────────────────────────────────────────────────┐ │ 1. Read plan, extract ALL tasks with full text │ │ 2. Note shared context (arch, deps, conventions) │ │ 3. Create TodoWrite with all tasks │ └──────────────────────┬──────────────────────────────┘ ▼ ┌────── Per Task ──────┐ │ │ │ Dispatch Implementer (references/implementer-prompt.md) │ │ │ │ ▼ │ │ Questions?──yes──► Answer, re-dispatch│ │ │no │ │ ▼ │ │ Implement + test + commit + self-review│ │ │ │ │ ▼ │ │ Dispatch Spec Reviewer (references/spec-reviewer-prompt.md) │ │ │ │ ▼ │ │ Compliant?──no──► Implementer fixes──┘ │ │yes then re-review │ ▼ │ Dispatch Code Reviewer (references/code-quality-reviewer-prompt.md) │ │ │ ▼ │ Approved?──no──► Implementer fixes, re-review │ │yes │ ▼ │ Mark task complete └───────┬──────────────┘ ▼ More tasks? ──yes──► next task │no ▼ Final cross-task code review ▼ Finish development branch ### Prompt Templates Three reference prompts are provided for the subagent roles: RoleFilePurposeImplementerreferences/implementer-prompt.mdImplement, test, commit, self-reviewSpec reviewerreferences/spec-reviewer-prompt.mdVerify code matches spec exactlyCode reviewerreferences/code-quality-reviewer-prompt.mdVerify code is clean and maintainable ### Example Workflow Controller: Reading plan — 5 tasks extracted, TodoWrite created. ─── Task 1: Hook installation script ─── [Dispatch implementer with full task text + context] Implementer: "Should the hook be installed at user or system level?" Controller: "User level (~/.config/hooks/)" Implementer: ✅ Implemented install-hook command - Added tests (5/5 passing) - Self-review: missed --force flag, added it - Committed [Dispatch spec reviewer] Spec reviewer: ✅ Spec compliant — all requirements met [Dispatch code reviewer with git SHAs] Code reviewer: ✅ Approved — clean, good coverage [Mark Task 1 complete] ─── Task 2: Recovery modes ─── [Dispatch implementer] Implementer: ✅ Added verify/repair modes (8/8 tests passing) [Dispatch spec reviewer] Spec reviewer: ❌ Issues: - Missing: progress reporting ("report every 100 items") - Extra: added --json flag (not in spec) [Implementer fixes: remove --json, add progress reporting] Spec reviewer: ✅ Spec compliant [Dispatch code reviewer] Code reviewer: Important — magic number 100, extract constant [Implementer fixes: extract PROGRESS_INTERVAL] Code reviewer: ✅ Approved [Mark Task 2 complete] ... (tasks 3-5) ... [Final cross-task code review] Final reviewer: ✅ All requirements met, ready to merge ### Controller Responsibilities The controller (you) orchestrates the flow. Key duties: ResponsibilityDetailExtract tasks upfrontRead plan once, extract all task text — subagents never read the plan fileProvide full contextGive each subagent the complete task text + architectural contextAnswer questionsRespond clearly and completely before letting subagent proceedEnforce review orderSpec compliance first, code quality second — never reversedTrack progressUpdate TodoWrite after each task completesDispatch sequentiallyOne implementation subagent at a time to avoid conflicts ### Quality Gates Each task passes through three quality checks: GateWhoWhatSelf-reviewImplementerCompleteness, naming, YAGNI, test qualitySpec reviewSpec reviewerMatches requirements exactly — nothing more, lessCode reviewCode reviewerClean code, maintainability, test coverage ### Advantages vs. manual execution: Fresh context per task (no confusion from accumulated state) Subagents follow TDD naturally Questions surfaced before work begins, not after vs. parallel-session plans: No handoff overhead Continuous progress Review checkpoints are automatic Cost trade-off: More subagent invocations (implementer + 2 reviewers per task), but catches issues early — cheaper than debugging later. ### NEVER Do Skip either review — both spec compliance and code quality are mandatory Start code review before spec review passes — wrong order wastes effort on code that doesn't meet spec Dispatch multiple implementers in parallel — causes merge conflicts and context corruption Make subagents read the plan file — provide full task text directly Skip scene-setting context — subagent needs to understand where the task fits architecturally Ignore subagent questions — answer fully before they proceed Accept "close enough" on spec compliance — if the reviewer found issues, it's not done Skip re-review after fixes — reviewer found issues → implementer fixes → reviewer reviews again Let self-review replace actual review — self-review is a first pass, not a substitute Move to next task with open review issues — current task must be fully approved first Fix issues manually instead of through a subagent — manual fixes pollute controller context ### Handling Failures SituationResponseSubagent asks questionsAnswer clearly, provide additional context if neededReviewer finds issuesSame implementer subagent fixes, reviewer re-reviewsSubagent fails task entirelyDispatch a new fix subagent with specific instructionsTask blocked by dependencyReorder remaining tasks or resolve dependency first ## Trust - Source: tencent - Verification: Indexed source record - Publisher: wpank - Version: 0.1.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-01T08:43:20.520Z - Expires at: 2026-05-08T08:43:20.520Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/subagent-driven-development-2) - [Send to Agent page](https://openagent3.xyz/skills/subagent-driven-development-2/agent) - [JSON manifest](https://openagent3.xyz/skills/subagent-driven-development-2/agent.json) - [Markdown brief](https://openagent3.xyz/skills/subagent-driven-development-2/agent.md) - [Download page](https://openagent3.xyz/downloads/subagent-driven-development-2)