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 AlexAI-MCP in AlexAI-MCP/hermes-CCC

Decompose Claude Code work into parallel subagent-friendly streams when the environment permits delegation.

MITAuto-check passedAgent Workflows

Install Subagent Driven Development

skills CLI
$ npx skills add AlexAI-MCP/hermes-CCC --skill subagent-driven-development -a claude-code

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

GitHub CLI
$ gh skill install AlexAI-MCP/hermes-CCC 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/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/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
135
Token cost
~1.6k tokens
SKILL.md length
732 words
Files
1
Skills in repo
44
Repo updated
First seen
Licence
MIT

At a glance

Decompose Claude Code work into parallel subagent-friendly streams when the environment permits delegation.

  • Works in 8 steps: Identify the deliverable. → Identify the next blocking action. → Keep that blocking action local. → …
  • A task has independent sidecar work
  • SKILL.md covers Purpose, Activation Signals, Non-Use Signals and Core Principle, plus 17 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Subagent Driven Development is an agent skill from AlexAI-MCP/hermes-CCC. Decompose Claude Code work into parallel subagent-friendly streams when the environment permits delegation. Use when a task has independent sidecar work, disjoint file ownership, or review/verification streams that can run in parallel without blocking the critical path.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents. The repository describes itself as: Hermes Agent ported to Claude Code Channel — 46 native skills, no OAuth, no external process. The licence is MIT.

When your agent uses it

  • A task has independent sidecar work
  • Disjoint file ownership
  • Review/verification streams that can run in parallel without blocking the critical path

Example prompts

  • “/subagent-driven-development”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Identify the deliverable.
  2. Identify the next blocking action.
  3. Keep that blocking action local.
  4. List other work that can advance in parallel.
  5. Split the work by independent outputs or disjoint write sets.
  6. Write one concrete prompt per subagent.
  7. State ownership and constraints clearly.
  8. Continue local progress immediately.

What it can do on your machine

Read from SKILL.md and the folder at commit 8107e89. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

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

  • Network

    No URLs in SKILL.md.

    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 1.6k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 732 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from AlexAI-MCP/hermes-CCC at commit 8107e89, republished under its MIT licence (© AlexAI-MCP). 732 words, ~1,593 tokens.

Download SKILL.mdSave it as .claude/skills/subagent-driven-development/SKILL.md (or your agent's skills folder).
name
subagent-driven-development
description
Decompose Claude Code work into parallel subagent-friendly streams when the environment permits delegation. Use when a task has independent sidecar work, disjoint file ownership, or review/verification streams that can run in parallel without blocking the critical path.
version
0.1.0
author
OpenAI Codex
license
MIT
metadata.category
orchestration
metadata.ported_from
NousResearch Hermes Agent
metadata.tags
subagents, parallelism, decomposition, coordination
metadata.tools
plan, subagents, review
metadata.maturity
beta

Subagent-Driven Development

Purpose

  • Shorten total task time by parallelizing independent work.
  • Keep the critical path moving locally while sidecar work runs elsewhere.
  • Prevent duplicated effort between contributors.
  • Improve reliability by separating implementation, research, and verification concerns.
  • Turn broad requests into explicit owned slices.

Activation Signals

  • Use this skill when the task has multiple independent questions.
  • Use this skill when write scopes can be separated cleanly.
  • Use this skill when verification can happen in parallel with implementation.
  • Use this skill when one thread can map code while another edits disjoint files.
  • Use this skill only if the environment allows subagent delegation.

Non-Use Signals

  • Do not use this skill when the user did not permit delegation.
  • Do not use this skill when the next local action is blocked on the answer.
  • Do not use this skill when the task is small enough to finish faster alone.
  • Do not use this skill when the subtasks touch the same files and will conflict.
  • Do not use this skill when the problem is still poorly framed.

Core Principle

  • Keep blocking work local.
  • Delegate bounded sidecar work.
  • Assign explicit ownership.
  • Integrate results quickly.
  • Do not re-do delegated work yourself.

Decomposition Procedure

  1. Identify the deliverable.
  2. Identify the next blocking action.
  3. Keep that blocking action local.
  4. List other work that can advance in parallel.
  5. Split the work by independent outputs or disjoint write sets.
  6. Write one concrete prompt per subagent.
  7. State ownership and constraints clearly.
  8. Continue local progress immediately.

Good Subtasks

  • codebase mapping for a specific subsystem
  • docs-backed verification
  • isolated backend patch in owned files
  • isolated frontend patch in owned files
  • targeted regression test creation in a separate file family
  • review of a completed patch

Bad Subtasks

  • "figure out the whole problem"
  • "do whatever seems useful"
  • work that overlaps the same file region
  • urgent work needed for the next local decision
  • tasks that duplicate what the main thread is already doing

Prompt Design Rules

  • State the task in one sentence first.
  • Name the owned files or module boundary.
  • Say that the subagent is not alone in the codebase.
  • Say not to revert other changes.
  • Define the expected final output.
  • Include any known constraints or acceptance tests.

Example Prompt

text
Implement the parser fix in parser/tokenizer.py only. You are not alone in the codebase, so do not revert unrelated edits and adjust to concurrent changes if needed. Return the files changed and a short note on verification.

Ownership Rules

  • One write owner per file family whenever possible.
  • Shared read-only context is fine.
  • Shared write scope is a last resort.
  • Verification agents should prefer read-only work unless asked to patch tests.

Waiting Rules

  • Do not wait immediately after delegation.
  • Use the time to do non-overlapping local work.
  • Wait only when integration is blocked on the result.
  • Prefer longer waits over frequent polling.
  • Close finished agents when they are no longer needed.
Show full SKILL.md (291 more words)Show less

Integration Procedure

  1. Review the returned output.
  2. Check whether the subtask stayed within scope.
  3. Read the changed files or summary.
  4. Integrate into the local branch carefully.
  5. Reconcile any assumptions that conflict with local work.
  6. Run the relevant validation.

Conflict Management

  • If two streams unexpectedly touch the same file, stop and replan.
  • Do not blindly merge contradictory changes.
  • Preserve the clearer ownership model after the replan.
  • Prefer one integrator making final decisions.

Verification Patterns

  • implementation locally, review remotely
  • implementation remotely, integration locally
  • code mapping remotely, coding locally
  • docs verification remotely, code changes locally

Fallback When Subagents Are Not Allowed

  • Use the same decomposition framework locally.
  • Convert each subagent slice into a checklist item.
  • Work the slices sequentially in priority order.
  • Preserve explicit ownership even if ownership is just "current thread".

Decision Rules

  • Delegate only if the subtask is concrete and bounded.
  • Keep ambiguity resolution local.
  • Parallelize information gathering aggressively when it is independent.
  • Avoid delegating more agents than the integration cost can support.
  • If the main path is short, skip delegation.

Common Failure Modes

  • delegation of blocking work
  • overlapping file ownership
  • weak prompts that encourage broad wandering
  • premature waiting
  • local duplication of delegated work

Recovery Moves

  • cancel or redirect a drifting subtask quickly
  • re-scope overlapping workers into disjoint ownership
  • absorb a small sidecar task locally if delegation overhead dominates
  • move verification later if implementation is still unstable

Output Contract

When presenting the decomposition, include:

  • local critical-path task
  • delegated sidecar tasks
  • ownership per task
  • integration point
  • validation plan

Example Decomposition Block

markdown
Local critical path: reproduce failing parser test and patch tokenizer logic
Delegated sidecar task: map config loading path in config/ only
Delegated verification task: draft regression tests under tests/parser/ only
Integration point: after tokenizer patch compiles
Validation plan: run targeted parser tests and review returned diffs

Checklist

  1. Identify the blocking task.
  2. Keep it local.
  3. Find parallel sidecar tasks.
  4. Split by disjoint ownership.
  5. Write precise prompts.
  6. Continue local work.
  7. Wait only when blocked.
  8. Integrate and validate.

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

Files

Just SKILL.md in skills/subagent-driven-development of AlexAI-MCP/hermes-CCC.

Open the folder on GitHubat commit 8107e89

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 skillAlexAI-MCP/hermes-CCC135—~1.6kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26138 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25841 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • 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 38 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 41 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-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 today
    Agent WorkflowsAuto-check passed

More from AlexAI-MCP/hermes-CCC

All 44 skills in this repo

  • GitHub Code Review

    AlexAI-MCP/hermes-CCC

    Review GitHub pull requests with a findings-first engineering mindset.

    135 GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed

  • GitHub PR Workflow

    AlexAI-MCP/hermes-CCC

    Run a disciplined GitHub pull request workflow from branch creation through merge.

    135 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed

  • Hermes Memory

    AlexAI-MCP/hermes-CCC

    Manage durable project memory for Claude Code. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed

  • Hermes Route

    AlexAI-MCP/hermes-CCC

    Route Claude Code work by complexity, risk, and tool needs. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed

  • Hermes Skill

    AlexAI-MCP/hermes-CCC

    Create, improve, inventory, and audit Claude Code skills. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed

  • Hermes Traj

    AlexAI-MCP/hermes-CCC

    Capture Claude Code interaction trajectories in training-friendly formats.

    135 GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Subagent Driven Development

What does Subagent Driven Development do?

Decompose Claude Code work into parallel subagent-friendly streams when the environment permits delegation. Subagent Driven Development is an agent skill from AlexAI-MCP/hermes-CCC. Decompose Claude Code work into parallel subagent-friendly streams when the environment permits delegation.

When should I use Subagent Driven Development?

Subagent Driven Development fits situations like: A task has independent sidecar work; disjoint file ownership; review/verification streams that can run in parallel without blocking the critical path.

How do I install Subagent Driven Development in Claude Code?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill subagent-driven-development -a claude-code`. Or copy the skill folder (skills/subagent-driven-development in AlexAI-MCP/hermes-CCC) 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 AlexAI-MCP/hermes-CCC --skill subagent-driven-development -a codex`. Or copy the skill folder (skills/subagent-driven-development in AlexAI-MCP/hermes-CCC) 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 AlexAI-MCP/hermes-CCC --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?

SKILL.md names no scripts, command-line tools or credentials: Subagent Driven Development is instructions for the agent only.

Does Subagent Driven Development access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. 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 MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Subagent Driven Development use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Subagent Driven Development?

Skills that share tags, products or a category with Subagent Driven Development: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k 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?

AlexAI-MCP (a GitHub user) maintains it in AlexAI-MCP/hermes-CCC, which has 135 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on April 8, 2026.

Source: AlexAI-MCP/hermes-CCC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.