subagent-driven-development is agent-read markdown (skill) from ganyuanran/aegis: Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Execute
→ Have an implementation plan with independent tasks? → **Fresh subagent per task + two-stage review.**
1. Read plan, extract all tasks, create TodoWrite
2. Per task: dispatch implementer → answer questions → implementer completes
3. Review stage 1 (spec compliance) → fix gaps → re-review until ✅
4. Review stage 2 (code quality) → fix issues → re-review until ✅
5. Coordinator verifies, commits the coherent task, updates checkpoint/drift → next task
→ All tasks done: final review → verification receipt; branch finishing only when needed.
# Subagent-Driven Development
Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
A 17 of 17 checks passed. Deterministic, no model, same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (9090 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
ganyuanran/aegis · 1,280 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tjzpwomeznf2w35z
GET https://markdownregistry.com/api/v1/resolve?ref=ganyuanran/aegis/subagent-driven-development
GET https://markdownregistry.com/api/v1/blob/0d7c1a36d5d018066d3f6fbb4bc904bd817cfccfc5ed1f162d9eabb0966f172a
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
ganyuanran/aegis · skills/brainstorming/SKILL.md · Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture…
ganyuanran/aegis · skills/communicating-concisely/SKILL.md · Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise…
ganyuanran/aegis · skills/dispatching-parallel-agents/SKILL.md · Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential…
ganyuanran/aegis · skills/establishing-project-context/SKILL.md · Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or…
ganyuanran/aegis · skills/executing-plans/SKILL.md · Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice…
ganyuanran/aegis · skills/finishing-a-development-branch/SKILL.md · Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly…
ganyuanran/aegis · skills/first-principles-review/SKILL.md · Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints…
ganyuanran/aegis · skills/goal-framing/SKILL.md · Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success…
ganyuanran/aegis · skills/long-task-continuation/SKILL.md · Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before…
a5c-ai/babysitter · library/methodologies/superpowers/skills/subagent-driven-development/SKILL.md · Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per…
coco-research/coco · skills/subagent-driven-development/SKILL.md · Use when executing implementation plans with independent tasks in the current session
jamditis/claude-skills-journalism · superjawn/skills/subagent-driven-development/SKILL.md · Use when executing implementation plans with independent tasks in the current session
arbiterforge/codearbiter · plugins/ca-pi/routines/subagent-driven-development/SKILL.md · The implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch…
arbiterforge/codearbiter · plugins/ca/skills/subagent-driven-development/SKILL.md · The implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch…
