New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Subagent-Driven Development

by HoangNguyen0403 in HoangNguyen0403/agent-skills-standard

Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.

MITAuto-check passedAgent Workflows

Install Subagent-Driven Development

skills CLI
$ npx skills add HoangNguyen0403/agent-skills-standard --skill common-subagent-driven-development -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HoangNguyen0403/agent-skills-standard common-subagent-driven-development --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/common/common-subagent-driven-development .claude/skills/common-subagent-driven-development && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
common-subagent-driven-development
GitHub stars
572
Token cost
~1.3k tokens
SKILL.md length
546 words
Files
9 (incl. scripts, references)
Skills in repo
211
Repo updated
First seen
Licence
MIT

At a glance

Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.

  • Works in 5 steps: Execution Confirmation Gate (Scenario A… → SDD & The Single Worker Contract → Setup & Workspace Resolution → …
  • Executing a written plan with several tasks that should each get a clean context
  • SKILL.md covers Priority: P1 (HIGH), 1. Execution Confirmation Gate…, 2. SDD & The Single Worker… and 3. Setup & Workspace Resolution, plus 4 more sections
  • Runs Python scripts from its folder; calls python3 and git

What it does

Before any code is touched, the agent asks you to confirm the approach: subagent-driven work for multi-task plans, or inline editing only for tiny changes of one or two files. The orchestrating session does not edit files itself. A helper script, sdd_workspace.py, sets up an isolated git-ignored workspace, and a progress.md file there tracks finished tasks so the work survives context compaction.

Each task goes through a loop. task_brief.py writes a brief, a cheaper-tier implementer subagent is dispatched with it and told to follow red, green, refactor, and the orchestrator waits without polling. review_package.py then builds a diff package for a task reviewer, and review findings go back to the same worker in a fix loop of up to 5 rounds.

When all tasks pass, a senior reviewer on the most capable model checks the whole branch, the workspace is deleted and the branch is completed. The skill lists anti-patterns: editing files directly in the orchestrator, polling loops and pasting full briefs or diffs into prompts instead of passing file paths. Reference files hold the methodology and prompt templates, and an evals file ships with it.

When your agent uses it

  • Executing a written plan with several tasks that should each get a clean context
  • Implementing a multi-task pull request with a review gate after every task
  • Moving from planning to implementation without bloating the main session

Example prompts

  • “Execute docs/plans/billing-migration.md task by task with a fresh subagent and a review for each.”
  • “Start implementing the approved plan, but check with me before dispatching any workers.”
  • “Review the whole branch with a senior reviewer once all plan tasks are done.”

Requirements

  • An agent environment that can dispatch subagents
  • Python 3 to run the helper scripts
  • A written multi-task implementation plan

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Execution Confirmation Gate (Scenario A & B)
  2. SDD & The Single Worker Contract
  3. Setup & Workspace Resolution
  4. The Task Loop
  5. Final Review & Completion

What it can do on your machine

Read from SKILL.md and the folder at commit b529c2d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Subagent-Driven Development loads about 1.3k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 546 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from HoangNguyen0403/agent-skills-standard at commit b529c2d, republished under its MIT licence (© HoangNguyen0403). 546 words, ~1,337 tokens.

Download SKILL.mdSave it as .claude/skills/common-subagent-driven-development/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
common-subagent-driven-development
description
Execute multi-task implementation plans by dispatching a fresh implementer subagent per task with independent review gates. Use when implementing plans, executing multi-task PRs, or transitioning from planning to implementation.

Subagent-Driven Development (SDD)

Priority: P1 (HIGH)

Execute multi-task implementation plans by dispatching a fresh implementer subagent per task, an independent task review (spec compliance + code quality) after each, and a whole-branch review at the end.

1. Execution Confirmation Gate (Scenario A & B)

Before editing code for any multi-task plan:

  1. DO NOT start editing files directly in this orchestrator session.
  2. Confirm with human partner: Host approval policy overrides defaults. Offer Subagent-Driven (Recommended — fresh workers per task for context isolation + task review gate) vs. Inline (direct implementation in orchestrator session for small bounded changes).
  3. If approved (or user replies "yes", "proceed", "start", "approve"), invoke SDD. See methodology.md.

2. SDD & The Single Worker Contract

  • Macro (SDD Orchestrator): Manages task decomposition, workspace isolation, brief generation, independent review gates, Git commits, and final integration verification.
  • Worker Contract: Implementer subagents own bounded implementation and focused verification of touched files. Workers do NOT commit changes with Git, recursively delegate to other agents, or run full project test suites by default.
  • Micro (TDD): Implementer subagents follow the RED -> GREEN -> REFACTOR cycle inside their assigned brief.

3. Setup & Workspace Resolution

Resolve the isolated, git-ignored workspace directory before Task 1:

bash
python3 skills/common/common-subagent-driven-development/scripts/sdd_workspace.py <PLAN_FILE>

Track task completion in <workspace>/progress.md so work survives context compaction.

Use the local version-2 explicit progress helper for revision/evidence-bound checkpoints; it does not enforce host pauses, authorization, or wakeups. See Progress Receipts.

4. The Task Loop

For each task in the plan:

  1. Record Baseline & Dispatch Implementer: Record BASE=$(git rev-parse HEAD). From the repository root, generate the brief with python3 skills/common/common-subagent-driven-development/scripts/task_brief.py <PLAN_FILE> <TASK_NUMBER>. Dispatch worker with [BRIEF_FILE] and [REPORT_FILE].
  2. Passive Wait (No Polling): Call wait() and yield control. Never poll status or activity in a loop.
  3. Scoped Review Package & Review: From the repository root, run python3 skills/common/common-subagent-driven-development/scripts/review_package.py <PLAN_FILE> $BASE WORKSPACE --paths <OWNED_PATHS...>. Workspace mode requires explicit literal file paths or bounded owned directories (no Git pathspec magic, globs, ., or overlapping scopes). Each changed workspace snapshot gets a content-addressed immutable default filename; same-base/scope packages are cumulative from $BASE, not fix-only. Dispatch reviewer with [BRIEF_FILE], [REPORT_FILE], and [DIFF_FILE].
  4. Fix Loop (Up to 5 Rounds): Re-prompt the worker; regenerate the cumulative package from the original $BASE and identical owned paths. The latest package includes all task changes through that round; re-review the open findings against that cumulative state and do not describe it as a fix-only diff.
  5. Orchestrator Integration: Orchestrator verifies diff, runs full suite checks if required, and creates git commit.
Show full SKILL.md (140 more words)Show less

5. Final Review & Completion

Run whole-branch review from the repository root: python3 skills/common/common-subagent-driven-development/scripts/review_package.py <PLAN_FILE> $MERGE_BASE HEAD. Dispatch senior reviewer on capable model. Once clean, delete <workspace> and complete branch.

Anti-Patterns

  • No Worker Commits: Workers leave edits in the workspace and report diffs/evidence; the orchestrator commits.
  • No Recursive Delegation: Implementers do not spawn subagents.
  • No Full-Suite Runs by Workers: Workers run focused tests; orchestrator runs broad verification during integration.
  • No Speculative Savings Claims: Describe context isolation factually, not with guaranteed percentages.
  • No Inline Edits on Multi-Task Plans: Do not burn orchestrator context editing files directly.
  • No Polling Loops: Yield control via wait(); do not loop get_agent_status.
  • No Inlined Context Bloat: Pass briefs and diffs as file paths, never paste full bodies into chat prompts.

References

© HoangNguyen0403, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in skills/common/common-subagent-driven-development of HoangNguyen0403/agent-skills-standard.

  • SKILL.md
  • evals/evals.json
  • references/methodology.md
  • references/progress-receipts.md
  • references/templates.md
  • scripts/review_package.py
  • scripts/sdd_progress.py
  • scripts/sdd_workspace.py
  • scripts/task_brief.py

Open the folder on GitHubat commit b529c2d

Compare with similar skills

Subagent-Driven Development next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Subagent-Driven Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Subagent-Driven Development this skillHoangNguyen0403/agent-skills-standard572—~1.3kAutomated safety check: PassMIT
Tbdjlevy/strif131—~3.5kAutomated safety check: PassMIT
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Clawteamwin4r/ClawTeam-OpenClaw1.5k—~3.1kAutomated safety check: PassMIT
Multi-Model Adversarial Reviewcursor/plugins11k8 repos~1.1kAutomated safety check: PassNone
agystack Runtime Setupjtaroreh/agystack112—~1.7kAutomated safety check: PassMIT

Similar skills

  • Tbd

    jlevy/strif

    Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents.

    131 GitHub stars~3.5k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Clawteam

    win4r/ClawTeam-OpenClaw

    Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.

    1.5k GitHub stars~3.1k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

  • Multi-Model Adversarial Review

    cursor/plugins

    Official

    Runs one read-only reviewer subagent per configured model against a diff to challenge a change, then synthesizes a single verdict without applying any fixes.

    11k GitHub starsUsed in 8 repos~1.1k tokens
    DevelopmentAuto-check passed

  • agystack Runtime Setup

    jtaroreh/agystack

    Configures agystack's model tiers per role and its execution runtime, choosing between local subagents and Cloud Run jobs for large parallel swarms.

    112 GitHub stars~1.7k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • Multi-Persona Code Review

    eric-tramel/moraine

    Coordinates a delegated review of a Moraine PR or local change by seven focused reviewer subagents, merges their findings and follows up on the fixes.

    117 GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed

More from HoangNguyen0403/agent-skills-standard

All 211 skills in this repo

  • draw.io Architecture Diagramming

    HoangNguyen0403/agent-skills-standard

    Draws architecture diagrams as editable draw.io files from a JSON spec, with a fixed house style, one C4 level per diagram and evidence-tagged shapes.

    572 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Android Navigation 3 Guide

    HoangNguyen0403/agent-skills-standard

    Implements and migrates to Jetpack Navigation 3 in Compose: NavDisplay, typed route objects, a state-list back stack, deep links, multiple back stacks and dialog scenes.

    572 GitHub stars~687 tokensUpdated yesterday
    Auto-check passed

  • Angular HttpClient Standards

    HoangNguyen0403/agent-skills-standard

    Sets rules for Angular HTTP code: functional interceptors, typed requests, services that own every call, and httpResource for reactive data loading in Angular 17+.

    572 GitHub stars~652 tokensUpdated yesterday
    Auto-check passed

  • Angular Tooling

    HoangNguyen0403/agent-skills-standard

    Angular CLI usage, code generation, build configuration, and bundle optimization.

    572 GitHub stars~743 tokensUpdated yesterday
    Auto-check passed

  • Common Code Review

    HoangNguyen0403/agent-skills-standard

    Conduct high-quality, persona-driven code reviews. An agent skill from HoangNguyen0403/agent-skills-standard.

    572 GitHub stars~772 tokensUpdated yesterday
    Auto-check passed

  • Common Feedback Reporter

    HoangNguyen0403/agent-skills-standard

    Pre-write audit for skill violations: checks planned code against loaded skill anti-patterns before any file write.

    572 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Subagent-Driven Development

What does Subagent-Driven Development do?

Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch. Before any code is touched, the agent asks you to confirm the approach: subagent-driven work for multi-task plans, or inline editing only for tiny changes of one or two files. The orchestrating session does not edit files itself.

When should I use Subagent-Driven Development?

Subagent-Driven Development fits situations like: executing a written plan with several tasks that should each get a clean context; implementing a multi-task pull request with a review gate after every task; moving from planning to implementation without bloating the main session.

How do I install Subagent-Driven Development in Claude Code?

Run `npx skills add HoangNguyen0403/agent-skills-standard --skill common-subagent-driven-development -a claude-code`. Or copy the skill folder (skills/common/common-subagent-driven-development in HoangNguyen0403/agent-skills-standard) into .claude/skills/common-subagent-driven-development in your project. Claude Code loads it when a task matches its description.

How do I install Subagent-Driven Development in Codex?

Run `npx skills add HoangNguyen0403/agent-skills-standard --skill common-subagent-driven-development -a codex`. Or copy the skill folder (skills/common/common-subagent-driven-development in HoangNguyen0403/agent-skills-standard) into .agents/skills/common-subagent-driven-development in your project. Codex loads it when a task matches its description.

Can I use Subagent-Driven Development in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HoangNguyen0403/agent-skills-standard --skill common-subagent-driven-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/common-subagent-driven-development, .gemini/skills/common-subagent-driven-development, .github/skills/common-subagent-driven-development and .opencode/skills/common-subagent-driven-development in your project.

What does Subagent-Driven Development need to run?

Going by SKILL.md and its folder, Subagent-Driven Development needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and git). Our summary lists: An agent environment that can dispatch subagents; Python 3 to run the helper scripts; A written multi-task implementation plan.

Does Subagent-Driven Development access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Subagent-Driven Development safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Subagent-Driven Development use?

Subagent-Driven Development is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Subagent-Driven Development use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.

What are the alternatives to Subagent-Driven Development?

Skills that share tags, products or a category with Subagent-Driven Development: Tbd (jlevy/strif, 131 stars), O2 Review Loop (openobserve/openobserve, 22k stars), Clawteam (win4r/ClawTeam-OpenClaw, 1.5k stars) and Multi-Model Adversarial Review (cursor/plugins, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Subagent-Driven Development?

HoangNguyen0403 (a GitHub user) maintains it in HoangNguyen0403/agent-skills-standard, which has 572 GitHub stars. The repository holds 211 skills in this directory. The repository was last updated on October 9, 2026.

Source: HoangNguyen0403/agent-skills-standard on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.