subagent-driven-development

subagent-driven-development is a skill for Claude Code, Codex from metaspartan/cybara. It costs 19 tokens per session (468 once invoked), scanned A, original, MIT.

A development workflow that gives separate implementation tasks to isolated helper agents, then checks their work against the specification and quality requirements.

In plain words
What is it for?
Use it for multi-part implementation plans with mostly independent tasks. It helps coordinate implementation, specification review, quality checks, and final integration.
Why use it?
It reduces confusion on larger plans by separating tasks and adding review before changes are integrated.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions subagents; built for openclaw.

Good fit Use it for multi-part implementation plans with mostly independent tasks. It helps coordinate implementation, specification review, quality checks, and final integration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metaspartan/cybara/subagent-driven-development
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add metaspartan/cybara --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/metaspartan/cybara

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for subagent-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/metaspartan/cybara/subagent-driven-development/github.svg)](https://agentmods.dev/skills/metaspartan/cybara/subagent-driven-development)
Your own site
<a href="https://agentmods.dev/skills/metaspartan/cybara/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/subagent-driven-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for subagent-driven-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/metaspartan/cybara/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00468
Opus 5 $0.00010 $0.00234
Sonnet 5 $0.00004 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured 9d ago against content hash cdb5e7fc07b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

subagent-driven-development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/subagent-driven-development/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent-Driven Development

Use this for larger implementation plans where independent work can be delegated and reviewed before integration.

This adapts the Hermes/OpenClaw subagent workflow to Cybara's sessions_spawn, sessions_send, sessions_history, session_status, todo, and kanban_* tools.

When To Use

  • The plan has multiple mostly independent tasks.
  • Fresh context per task reduces confusion.
  • You need an implementer plus a spec reviewer and quality reviewer.
  • The user explicitly asks for subagents or parallel implementation.

Do not use it for small single-file fixes; direct implementation is faster and clearer.

Workflow

  1. Read the plan once and extract every task with full context.
  2. Create a todo list with all task IDs.
  3. For each task:
    • Spawn an implementer session with the exact task, relevant files, constraints, and verification command.
    • After implementation, spawn or reuse a reviewer for spec compliance.
    • Then run a quality/security/test review.
    • Fix gaps and re-review before marking complete.
  4. After all tasks, run a final integration review across the full diff.
  5. Run the affected test suite and full project checks required by the repo.

Implementer Prompt Shape

Include:

  • Task text copied from the plan.
  • Files likely involved.
  • Project constraints such as package manager, test command, platform, and style.
  • Definition of done.
  • A request to avoid unrelated refactors and avoid committing unless instructed.

Reviewer Prompt Shape

Spec reviewer:

  • "Compare implementation to this exact task spec."
  • "Output PASS or specific gaps with file paths."

Quality reviewer:

  • "Check correctness, security, performance, tests, and maintainability."
  • "Output Critical, Important, Minor, and Verdict."

Rules

  • Never make subagents infer missing requirements from the full plan; pass the relevant task context directly.
  • Review receipts count only after both spec and quality review are complete.
  • Keep worktree ownership explicit. Do not let parallel agents edit the same files without coordination.
  • Final integration review is mandatory for cross-task behavior.

Read the full file on GitHub · 62 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 62 lines · 19 tokens per session scan A cdb5e7fc07b9

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository metaspartan/cybara (30 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 468 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.