Agent skill

Subagent Driven Development

by mateaix in mateaix/mateclaw

Execute plans via delegatetask subagents (2-stage review). An agent skill from mateaix/mateclaw.

Apache-2.0Auto-check passedAgent Workflows

Install Subagent Driven Development

skills CLI
$ npx skills add mateaix/mateclaw --skill subagent-driven-development -a claude-code

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

GitHub CLI
$ gh skill install mateaix/mateclaw 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/mateaix/mateclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mateclaw-server/src/main/resources/skills/subagent-driven-development .claude/skills/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
subagent-driven-development
GitHub stars
1.1k
Used in
3 other repos
Token cost
~2.6k tokens
SKILL.md length
752 words
Files
3 (incl. references)
Skills in repo
17
Repo updated
First seen
Licence
Apache-2.0

At a glance

Execute plans via delegatetask subagents (2-stage review). An agent skill from mateaix/mateclaw.

  • Works in 4 steps: Read and Parse Plan → Per-Task Workflow → Final Review → …
  • Tasks that involve Subagents
  • SKILL.md covers Overview, When to Use, The Process and Task Granularity, plus 7 more sections
  • Calls git and pytest

What it does

Subagent Driven Development is an agent skill from mateaix/mateclaw. Execute plans via delegatetask subagents (2-stage review).

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/context-budget-discipline.md` and `references/gates-taxonomy.md`).

It sits in Agent Workflows, covering Subagents and Planning. The repository describes itself as: 🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Subagents
  • Tasks that involve Planning

Example prompts

  • “/subagent-driven-development”

Requirements

  • Python 3

Workflow steps

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

  1. Read and Parse Plan
  2. Per-Task Workflow
  3. Final Review
  4. Verify and Commit

What it can do on your machine

Read from SKILL.md and the folder at commit 3b5f7de. 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

    Shell commands in SKILL.md call:

    • git
    • pytest

    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 2.6k tokens when it runs, and up to ~4.8k if it reads all its reference files. Until then it costs about 22 tokens; SKILL.md has 752 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.8k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from mateaix/mateclaw at commit 3b5f7de, republished under its Apache-2.0 licence (© mateaix). 752 words, ~2,628 tokens.

Download SKILL.mdSave it as .claude/skills/subagent-driven-development/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
subagent-driven-development
description
Execute plans via delegate_task subagents (2-stage review).
version
1.1.0
tags
delegation, subagent, implementation, workflow, parallel
author
ported

Subagent-Driven Development

Overview

Execute implementation plans by dispatching fresh subagents per task with systematic two-stage review.

Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.

When to Use

Use this skill when:

  • You have an implementation plan (from writing-plans skill or user requirements)
  • Tasks are mostly independent
  • Quality and spec compliance are important
  • You want automated review between tasks

vs. manual execution:

  • Fresh context per task (no confusion from accumulated state)
  • Automated review process catches issues early
  • Consistent quality checks across all tasks
  • Subagents can ask questions before starting work

The Process

1. Read and Parse Plan

Read the plan file. Extract ALL tasks with their full text and context upfront. Create a todo list:

python
# Read the plan
read_file("docs/plans/feature-plan.md")

# Create todo list with all tasks
todo([
    {"id": "task-1", "content": "Create User model with email field", "status": "pending"},
    {"id": "task-2", "content": "Add password hashing utility", "status": "pending"},
    {"id": "task-3", "content": "Create login endpoint", "status": "pending"},
])

Key: Read the plan ONCE. Extract everything. Don't make subagents read the plan file — provide the full task text directly in context.

2. Per-Task Workflow

For EACH task in the plan:

Step 1: Dispatch Implementer Subagent

Use delegate_task with complete context:

python
delegate_task(
    goal="Implement Task 1: Create User model with email and password_hash fields",
    context="""
    TASK FROM PLAN:
    - Create: src/models/user.py
    - Add User class with email (str) and password_hash (str) fields
    - Use bcrypt for password hashing
    - Include __repr__ for debugging

    FOLLOW TDD:
    1. Write failing test in tests/models/test_user.py
    2. Run: pytest tests/models/test_user.py -v (verify FAIL)
    3. Write minimal implementation
    4. Run: pytest tests/models/test_user.py -v (verify PASS)
    5. Run: pytest tests/ -q (verify no regressions)
    6. Commit: git add -A && git commit -m "feat: add User model with password hashing"

    PROJECT CONTEXT:
    - Python 3.11, Flask app in src/app.py
    - Existing models in src/models/
    - Tests use pytest, run from project root
    - bcrypt already in requirements.txt
    """,
    toolsets=['terminal', 'file']
)
Step 2: Dispatch Spec Compliance Reviewer

After the implementer completes, verify against the original spec:

python
delegate_task(
    goal="Review if implementation matches the spec from the plan",
    context="""
    ORIGINAL TASK SPEC:
    - Create src/models/user.py with User class
    - Fields: email (str), password_hash (str)
    - Use bcrypt for password hashing
    - Include __repr__

    CHECK:
    - [ ] All requirements from spec implemented?
    - [ ] File paths match spec?
    - [ ] Function signatures match spec?
    - [ ] Behavior matches expected?
    - [ ] Nothing extra added (no scope creep)?

    OUTPUT: PASS or list of specific spec gaps to fix.
    """,
    toolsets=['file']
)

If spec issues found: Fix gaps, then re-run spec review. Continue only when spec-compliant.

Step 3: Dispatch Code Quality Reviewer

After spec compliance passes:

python
delegate_task(
    goal="Review code quality for Task 1 implementation",
    context="""
    FILES TO REVIEW:
    - src/models/user.py
    - tests/models/test_user.py

    CHECK:
    - [ ] Follows project conventions and style?
    - [ ] Proper error handling?
    - [ ] Clear variable/function names?
    - [ ] Adequate test coverage?
    - [ ] No obvious bugs or missed edge cases?
    - [ ] No security issues?

    OUTPUT FORMAT:
    - Critical Issues: [must fix before proceeding]
    - Important Issues: [should fix]
    - Minor Issues: [optional]
    - Verdict: APPROVED or REQUEST_CHANGES
    """,
    toolsets=['file']
)

If quality issues found: Fix issues, re-review. Continue only when approved.

Step 4: Mark Complete
python
todo([{"id": "task-1", "content": "Create User model with email field", "status": "completed"}], merge=True)
3. Final Review

After ALL tasks are complete, dispatch a final integration reviewer:

python
delegate_task(
    goal="Review the entire implementation for consistency and integration issues",
    context="""
    All tasks from the plan are complete. Review the full implementation:
    - Do all components work together?
    - Any inconsistencies between tasks?
    - All tests passing?
    - Ready for merge?
    """,
    toolsets=['terminal', 'file']
)
4. Verify and Commit
bash
# Run full test suite
pytest tests/ -q

# Review all changes
git diff --stat

# Final commit if needed
git add -A && git commit -m "feat: complete [feature name] implementation"

Task Granularity

Each task = 2-5 minutes of focused work.

Too big:

  • "Implement user authentication system"

Right size:

  • "Create User model with email and password fields"
  • "Add password hashing function"
  • "Create login endpoint"
  • "Add JWT token generation"
  • "Create registration endpoint"

Red Flags — Never Do These

  • Start implementation without a plan
  • Skip reviews (spec compliance OR code quality)
  • Proceed with unfixed critical/important issues
  • Dispatch multiple implementation subagents for tasks that touch the same files
  • Make subagent read the plan file (provide full text in context instead)
  • Skip scene-setting context (subagent needs to understand where the task fits)
  • Ignore subagent questions (answer before letting them proceed)
  • Accept "close enough" on spec compliance
  • Skip review loops (reviewer found issues → implementer fixes → review again)
  • Let implementer self-review replace actual review (both are needed)
  • Start code quality review before spec compliance is PASS (wrong order)
  • Move to next task while either review has open issues

Handling Issues

If Subagent Asks Questions
  • Answer clearly and completely
  • Provide additional context if needed
  • Don't rush them into implementation
If Reviewer Finds Issues
  • Implementer subagent (or a new one) fixes them
  • Reviewer reviews again
  • Repeat until approved
  • Don't skip the re-review
If Subagent Fails a Task
  • Dispatch a new fix subagent with specific instructions about what went wrong
  • Don't try to fix manually in the controller session (context pollution)
Show full SKILL.md (300 more words)Show less

Efficiency Notes

Why fresh subagent per task:

  • Prevents context pollution from accumulated state
  • Each subagent gets clean, focused context
  • No confusion from prior tasks' code or reasoning

Why two-stage review:

  • Spec review catches under/over-building early
  • Quality review ensures the implementation is well-built
  • Catches issues before they compound across tasks

Cost trade-off:

  • More subagent invocations (implementer + 2 reviewers per task)
  • But catches issues early (cheaper than debugging compounded problems later)

Integration with Other Skills

With writing-plans

This skill EXECUTES plans created by the writing-plans skill:

  1. User requirements → writing-plans → implementation plan
  2. Implementation plan → subagent-driven-development → working code
With test-driven-development

Implementer subagents should follow TDD:

  1. Write failing test first
  2. Implement minimal code
  3. Verify test passes
  4. Commit

Include TDD instructions in every implementer context.

With requesting-code-review

The two-stage review process IS the code review. For final integration review, use the requesting-code-review skill's review dimensions.

With systematic-debugging

If a subagent encounters bugs during implementation:

  1. Follow systematic-debugging process
  2. Find root cause before fixing
  3. Write regression test
  4. Resume implementation

Example Workflow

[Read plan: docs/plans/auth-feature.md]
[Create todo list with 5 tasks]

--- Task 1: Create User model ---
[Dispatch implementer subagent]
  Implementer: "Should email be unique?"
  You: "Yes, email must be unique"
  Implementer: Implemented, 3/3 tests passing, committed.

[Dispatch spec reviewer]
  Spec reviewer: ✅ PASS — all requirements met

[Dispatch quality reviewer]
  Quality reviewer: ✅ APPROVED — clean code, good tests

[Mark Task 1 complete]

--- Task 2: Password hashing ---
[Dispatch implementer subagent]
  Implementer: No questions, implemented, 5/5 tests passing.

[Dispatch spec reviewer]
  Spec reviewer: ❌ Missing: password strength validation (spec says "min 8 chars")

[Implementer fixes]
  Implementer: Added validation, 7/7 tests passing.

[Dispatch spec reviewer again]
  Spec reviewer: ✅ PASS

[Dispatch quality reviewer]
  Quality reviewer: Important: Magic number 8, extract to constant
  Implementer: Extracted MIN_PASSWORD_LENGTH constant
  Quality reviewer: ✅ APPROVED

[Mark Task 2 complete]

... (continue for all tasks)

[After all tasks: dispatch final integration reviewer]
[Run full test suite: all passing]
[Done!]

Remember

Fresh subagent per task
Two-stage review every time
Spec compliance FIRST
Code quality SECOND
Never skip reviews
Catch issues early

Quality is not an accident. It's the result of systematic process.

Further reading (load when relevant)

When the orchestration involves significant context usage, long review loops, or complex validation checkpoints, load these references for the specific discipline:

  • references/context-budget-discipline.md — Four-tier context degradation model (PEAK / GOOD / DEGRADING / POOR), read-depth rules that scale with context window size, and early warning signs of silent degradation. Load when a run will clearly consume significant context (multi-phase plans, many subagents, large artifacts).
  • references/gates-taxonomy.md — The four canonical gate types (Pre-flight, Revision, Escalation, Abort) with behavior, recovery, and examples. Load when designing or reviewing any workflow that has validation checkpoints — use the vocabulary explicitly so each gate has defined entry, failure behavior, and resumption rules.

Both references adapted from gsd-build/get-shit-done (MIT © 2025 Lex Christopherson).

© mateaix, Apache-2.0. 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 2 other files (references) in mateclaw-server/src/main/resources/skills/subagent-driven-development of mateaix/mateclaw.

  • SKILL.md
  • references/context-budget-discipline.md
  • references/gates-taxonomy.md

Open the folder on GitHubat commit 3b5f7de

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in mateaix/mateclaw, which our catalogue first saw on October 7, 2026.

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 skillmateaix/mateclaw1.1k3 repos~2.6kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone
Executing PlansGanyuanRan/Aegis1.3k1 repos~2.3kAutomated safety check: PassMIT
Execumputun/cc-thingz483—~8kAutomated safety check: PassMIT
Autopilot End-to-End Buildernick-vels/skills403—~2.5kAutomated safety check: NotesMIT
Workflow Orchestrationvxcozy/workflow-orchestration115—~1kAutomated safety check: PassMIT

Similar skills

  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Executing Plans

    GanyuanRan/Aegis

    A skill your agent uses when executing a written implementation plan across sessions or with review checkpoints.

    1.3k GitHub starsUsed in 1 repo~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Exec

    umputun/cc-thingz

    Execute plan tasks sequentially using subagents. An agent skill from umputun/cc-thingz.

    483 GitHub stars~8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Builds an app, site, bot or feature from a spoken idea through requirements, spec, tickets, subagent work, review and acceptance, with a live progress dashboard.

    403 GitHub stars~2.5k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check: notes
  • Workflow Orchestration

    vxcozy/workflow-orchestration

    Disciplined task execution with planning, verification, and self-improvement loops.

    115 GitHub stars~1k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • Blueprint

    byungjunjang/jangpm-meta-skills

    Agentic system design blueprint generator. An agent skill from byungjunjang/jangpm-meta-skills.

    121 GitHub stars~2k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

More from mateaix/mateclaw

All 17 skills in this repo
  • Pixel Art

    mateaix/mateclaw

    Pixel art w/ era palettes (NES, Game Boy, PICO-8). An agent skill from mateaix/mateclaw.

    1.1k GitHub starsUsed in 5 repos~1.8k tokens
    Auto-check passed
  • DOCX

    mateaix/mateclaw

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).

    1.1k GitHub stars~4.1k tokensUpdated 2 days ago
    Auto-check passed
  • XLSX

    mateaix/mateclaw

    Use this skill any time a spreadsheet file is the primary input or output.

    1.1k GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Ideation

    mateaix/mateclaw

    Generate project ideas via creative constraints. An agent skill from mateaix/mateclaw.

    1.1k GitHub starsUsed in 2 repos~1.5k tokens
    Auto-check passed
  • Architecture Diagram

    mateaix/mateclaw

    Dark-themed SVG architecture/cloud/infra diagrams as HTML. An agent skill from mateaix/mateclaw.

    1.1k GitHub starsUsed in 5 repos~1.7k tokens
    Auto-check passed
  • Officecli

    mateaix/mateclaw

    Use the optional iOfficeAI/OfficeCLI engine for advanced inspection, validation, copy-on-write editing, template merge, or visual rendering of existing .docx, .xlsx, and .pptx files.

    1.1k GitHub stars~844 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Subagent Driven Development

What does Subagent Driven Development do?

Execute plans via delegatetask subagents (2-stage review). An agent skill from mateaix/mateclaw. Subagent Driven Development is an agent skill from mateaix/mateclaw. Execute plans via delegatetask subagents (2-stage review).

When should I use Subagent Driven Development?

Subagent Driven Development fits situations like: tasks that involve Subagents; tasks that involve Planning.

How do I install Subagent Driven Development in Claude Code?

Run `npx skills add mateaix/mateclaw --skill subagent-driven-development -a claude-code`. Or copy the skill folder (mateclaw-server/src/main/resources/skills/subagent-driven-development in mateaix/mateclaw) into .claude/skills/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 mateaix/mateclaw --skill subagent-driven-development -a codex`. Or copy the skill folder (mateclaw-server/src/main/resources/skills/subagent-driven-development in mateaix/mateclaw) into .agents/skills/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 mateaix/mateclaw --skill 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/subagent-driven-development, .gemini/skills/subagent-driven-development, .github/skills/subagent-driven-development and .opencode/skills/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 the command-line tools its instructions call (git and pytest). Our summary lists: Python 3.

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. Review the folder before installing.

What licence does Subagent Driven Development use?

Subagent Driven Development is published under the Apache-2.0 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 2.6k tokens (SKILL.md is roughly 11k 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 2.2k 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: Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Executing Plans (GanyuanRan/Aegis, 1.3k stars), Exec (umputun/cc-thingz, 483 stars) and Autopilot End-to-End Builder (nick-vels/skills, 403 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?

mateaix (a GitHub user) maintains it in mateaix/mateclaw, which has 1,147 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 5, 2026.

Source: mateaix/mateclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.