hoangnguyen0403/agent-skills-standard/common-subagent-driven-development

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Execute an approved implementation plan at the context boundary that preserves required independence and review. Use when implementing plans, executing multi-task PRs, choosing between main-loop and dispatched execution, or transitioning from planning to implementation.

Install

npx vskill@latest install hoangnguyen0403/agent-skills-standard/common-subagent-driven-development

SKILL.md

Subagent-Driven Development (SDD)

Priority: P1 (HIGH)

Execute a multi-task plan with one implementation owner per slice, independent review after each task, and whole-branch review before completion.

1. Placement Decision

Choose placement before any edit. Delegate only when at least one named benefit applies: independent parallel work over disjoint owned paths that are verifiable alone; measured context pressure such as observed truncation, lost constraints, or replay cost; a required independent verification gate that must be a separate owner from the implementer; or real host-enforced permission isolation, meaning the host enforces the boundary because prompt text is not enforcement. A specialist label, another workflow stage, file count, plan length, or "more thorough" fan-out is not a named benefit.

Precedence, first match wins: controlling host authority, then required independence or isolation, then coupling and verifiability, then economical eligible capability (common-task-complexity-routing).

ConditionPlacement
Coupled sequential reasoning; host permits main-loop implementationOne implementation context, skills loaded progressively
Independent, bounded, verifiable slices with disjoint ownershipConcurrent bounded workers, one owner per component
Host requires worker executionThat boundary; keep coupled steps in one bounded worker, not a planner/fixer chain
Isolation or permission needed but unavailableReport the operation unsupported or blocked; never infer permission

One implementation context is not one actor for the lifecycle: main-loop implementation still requires a separate reviewer, and a single worker still requires independent review.

  • Record the decision with its named benefit, or the host requirement that forced it. Reuse an approach the plan already records; do not re-ask.
  • Missing required approval, packet, standards, or isolation stops only the affected operation. Report the exact missing item; do not infer permission or silently change the execution path.
  • Plan approval authorizes neither merge, deployment, premium spend, nor a different execution mode.

2. Lifecycle

OperationRequired evidence
prepareStandalone packet: assignment manifest, task text, authority, invariants, owner, owned paths, required standards with revision, ACs, verification, source/dependency identities
dispatchOne implementation owner per slice; authority and data eligibility checked before any task context is sent
completionTerminal state reported by the host, not inferred from silence or elapsed time
resumeSame task, same authority, same owned paths; a new task is a fresh dispatch
cancelReported as cancelled/stopped; never as completed or verified
receiptOperation, task/actor/revision, terminal state, evidence, limitations
verify acceptanceIndependent reviewer, separate from the implementer, against ACs and evidence

Host instructions bind these operations to native invocation; canonical text names semantics only. If a required operation or permission control is unavailable on the host surface, report the affected operation unsupported; do not claim success. Dispatch, sequencing and recovery detail: Methodology.

3. Task Loop

  1. Select placement and prepare: Apply Section 1 and record the decision. Record BASE=$(git rev-parse HEAD). Generate the packet with task_brief.py <PLAN_FILE> <TASK_NUMBER> --assignment <ASSIGNMENT_JSON> --out <BRIEF_FILE>. The assignment manifest is required; never dispatch a bare task section.
  2. Execute or dispatch: One implementer per task when the placement decision requires it; otherwise execute the slice in the recorded single context. The packet, not repeated prose, carries authority and acceptance.
  3. Yield: Wait for a completion notification; never poll status in a loop.
  4. Review: Generate the scoped cumulative package from $BASE and the owned paths. Dispatch an independent reviewer with brief, report and package. Implementer self-review never satisfies this gate.
  5. Fix: Re-prompt the same worker with concrete failed ACs; regenerate the cumulative package and re-review against cumulative state.
  6. Integrate: Orchestrator verifies the diff, runs required covering checks, and commits.

4. Failure-Specific Recovery

Observed failureRoute
Missing prerequisite/contextneeds_context or blocked with the exact missing item; no fallback
Defective outputOne corrective assignment naming the failed AC and expected result
Observed provider exhaustionOnly an eligible, authorized fallback; the receipt records the exhaustion evidence and selected route
Consequential safety/design issueHuman decision

Retry count alone never authorizes premium. Timeout and cancellation are not completion. Required human approvals remain external to agent verdicts.

5. Final Review and Evidence

Run whole-branch review on a capable host hint, then complete the branch. Before deleting the workspace, archive packets, reports, immutable review snapshots and verification receipts at durable references; cleanup must not invalidate handoff links.

Anti-Patterns

  • No worker commits: workers leave changes; the orchestrator commits.
  • No recursive delegation: workers do not spawn agents.
  • No self-approval: implementer verdicts do not satisfy independent review.
  • No agent per stage: a workflow stage, specialist label, or file count never justifies a new agent; no named benefit, no dispatch.
  • No polling loops: yield until a completion event.
  • No fabricated savings or enforcement claims: prompt text is not a sandbox, and savings need complete measured coverage.

References

Methodology & Gates · Prompt Templates · Progress Receipts · Capability & Effort Resolution

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
577
Repository forks
165
7-day trend score
37

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/hoangnguyen0403/agent-skills-standard/common-subagent-driven-development/badge)](https://verified-skill.com/skills/hoangnguyen0403/agent-skills-standard/common-subagent-driven-development)

Something wrong with this skill or its page? Tell us.