subagent-driven-development

A way to carry out a multi-part coding plan with a fresh implementer and reviewer for each task. Each task has a clear handoff, focused tests, and a separate review before the next task begins.

In plain words
What is it for?
It helps split an approved plan into independent tasks, pass only the needed repository context, inspect changes, run focused tests, review the result, and return to design when the plan conflicts with the code.
Why use it?
Separate contexts reduce the chance that an author overlooks problems in their own work. Task boundaries also make parallel or complex changes easier to check and combine.

Skill for Claude CodeCodex

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.

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

Made for: Claude Code, Codex.

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00073 $0.00453
Opus 5 $0.00036 $0.00227
Sonnet 5 $0.00015 $0.00091
Haiku 4.5 $0.00007 $0.00045

Measured 2d ago against content hash ebc78d28e41f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 52 lines

What it actually says

Subagent-Driven Development

Use fresh context to reduce author bias, while keeping the plan and evidence as the shared contract.

Before dispatch

  • Confirm the design and implementation plan are approved.
  • Create or select an isolated workspace when concurrent edits need it.
  • Split the plan into tasks with disjoint ownership and explicit interfaces.
  • Define the focused test and review gate for each task.
  • Prepare a compact handoff packet from handoff-packet.md. Include verified facts and portable anchors, not a full conversation dump or the expected solution.

Per-task cycle

  1. Give the implementer the handoff packet, repository rules, and only the context needed for the task. Ask it to edit the files directly and report evidence.
  2. Inspect the implementation diff and run the focused test yourself.
  3. Give a fresh reviewer the task contract, diff, and test output—not the implementer's private reasoning or your expected answer.
  4. Validate every finding against the real code path.
  5. Fix in scope, rerun proof, and only then dispatch the next task.

If a task reveals a design contradiction, stop and return to solution-design/implementation-planning; do not make the subagent silently redesign the system. Keep unrelated agents independent and close them when finished.

Integration

The coordinator owns final interfaces, conflict resolution, broader tests, and the completion claim. Agent success is an input, never final evidence. Use requesting-code-review for a final aggregate review and completion-verification for closure.

Completion condition

Every task has implementer evidence and reviewer disposition, the integrated branch passes its relevant checks, and remaining limits are visible.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 52 lines · 73 tokens per session scan A ebc78d28e41f

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository thiientv/godmode (93 stars, last pushed 7d ago), licensed MIT. It adds 73 tokens to every session and 453 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

rulesync

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.

dyoshikawa/rulesync · 64 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

echo

Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.

cwinvestments/memstack · 35 tokens

backend-builder

Используй только внутри активного Codex Project Autopilot-проекта по утверждённому плану; не включай для обычных backend-задач вне автопилота.

hashgraph-online/awesome-codex-plugins · 43 tokens