subagent-driven-development SKILL.md skillA

subagent-driven-development from brandonfla/bearpaws is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add brandonfla/bearpaws/subagent-driven-development@git:20261002.3a8121c

Pins git:20261002.3a8121c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
brandonfla/bearpaws
Path
skills/subagent-driven-development/SKILL.md
Versions recorded
5
Latest version
git:20261002.3a8121c, committed Oct 2, 2026
First version recorded
May 1, 2026
Size
5,174 bytes
Repository stars
4
License
MIT

Use when executing implementation plans with independent tasks in the current session.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

<skill>

  <purpose>
    Execute plan by dispatching fresh subagent per task, with independent review after each. Routine tasks get one combined review (spec compliance and code quality); elevated-risk tasks get two stages: spec compliance first, then code quality.
  </purpose>

  <triggers>
    <rule>Use when you have an implementation plan and the user chose subagent-driven execution.</rule>
    <rule>Use when tasks are mostly independent and you're staying in this session.</rule>
  </triggers>

  <flow format="dot">
    ```dot
    digraph when_to_use {
      "Have plan?" [shape=diamond];
      "Tasks independent?" [shape=diamond];
      "Stay in session?" [shape=diamond];
      "subagent-driven-dev" [shape=box];
      "executing-plans" [shape=box];
      "brainstorm first" [shape=box];

      "Have plan?" -> "Tasks independent?" [label="yes"];
      "Have plan?" -> "brainstorm first" [label="no"];
      "Tasks independent?" -> "Stay in session?" [label="yes"];
      "Tasks independent?" -> "brainstorm first" [label="tightly coupled"];
      "Stay in session?" -> "subagent-driven-dev" [label="yes"];
      "Stay in session?" -> "executing-plans" [label="parallel session"];
    }
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add brandonfla/bearpaws/subagent-driven-development@sha256:3fe26f92fe400de9

The line at the top of this page pins the label git:20261002.3a8121c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ssud32g6jvqldc5j.svg)](https://markdownregistry.com/a/art_ssud32g6jvqldc5j)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between May 1, 2026 and Oct 2, 2026, about one every 38 days.

versioncommittedcommitsizeaudit
git:20261002.3a8121c latest2026-10-02 3a8121c 5,174 BA view · diff
git:20261002.45a5f112026-10-02 45a5f11 5,384 BA view · diff
git:20260930.52fa1552026-09-30 52fa155 5,009 BA view · diff
git:20260929.12977112026-09-29 1297711 4,175 BA view · diff
git:20260501.de635682026-05-01 de63568 4,086 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (5174 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

brandonfla/bearpaws · 4 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ssud32g6jvqldc5j
GET https://markdownregistry.com/api/v1/resolve?ref=brandonfla/bearpaws/subagent-driven-development
GET https://markdownregistry.com/api/v1/blob/3fe26f92fe400de979ea18e49757f102dba3a446581ad46cde8dd271aff2be14

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from brandonfla/bearpaws

AGENTS.md AGENTS.md file
brandonfla/bearpaws · AGENTS.md
git:20260501.402017b · audit B · 4 stars
CLAUDE.md CLAUDE.md file
brandonfla/bearpaws · CLAUDE.md
git:20261105.a0bb798 · audit A · 4 stars
brainstorming SKILL.md skill
brandonfla/bearpaws · skills/brainstorming/SKILL.md · Use when about to create or change features, components, or behavior and the design has not been agreed yet
git:20260929.1297711 · audit A · 4 stars
dispatching-parallel-agents SKILL.md skill
brandonfla/bearpaws · skills/dispatching-parallel-agents/SKILL.md · Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
git:20260929.1297711 · audit A · 4 stars
executing-plans SKILL.md skill
brandonfla/bearpaws · skills/executing-plans/SKILL.md · Use when you have a written implementation plan to execute in a separate session with review checkpoints
git:20261002.3a8121c · audit A · 4 stars
finishing-a-development-branch SKILL.md skill
brandonfla/bearpaws · skills/finishing-a-development-branch/SKILL.md · Use when implementation on a branch is complete, tests pass, and it's time to decide how to integrate the work (merge…
git:20261105.a0bb798 · audit A · 4 stars
onboarding-to-a-project SKILL.md skill
brandonfla/bearpaws · skills/onboarding-to-a-project/SKILL.md · Applies when a session involves an existing codebase or project context and onboarding should occur prior to…
git:20261103.b29db48 · audit A · 4 stars
receiving-code-review SKILL.md skill
brandonfla/bearpaws · skills/receiving-code-review/SKILL.md · Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or…
git:20260929.1297711 · audit A · 4 stars
requesting-code-review SKILL.md skill
brandonfla/bearpaws · skills/requesting-code-review/SKILL.md · Use when completing tasks, implementing major features, or before merging to verify work meets requirements
git:20260930.642c5d3 · audit A · 4 stars
systematic-debugging SKILL.md skill
brandonfla/bearpaws · skills/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
git:20260501.de63568 · audit A · 4 stars
test-driven-development SKILL.md skill
brandonfla/bearpaws · skills/test-driven-development/SKILL.md · Use when implementing any feature or bugfix, before writing implementation code
git:20260501.88e4ec8 · audit A · 4 stars
using-bearpaws SKILL.md skill
brandonfla/bearpaws · skills/using-bearpaws/SKILL.md · Use when starting any conversation, before responding or exploring the project
git:20261103.59550d9 · audit A · 4 stars

Every file in brandonfla/bearpaws

Other files named subagent-driven-development

subagent-driven-development SKILL.md skill
obra/superpowers · skills/subagent-driven-development/SKILL.md · Use when executing implementation plans with independent tasks in the current session
git:20261103.22f0b46 · audit A · 314,583 stars
subagent-driven-development SKILL.md skill
jnmetacode/superpowers-zh · skills/subagent-driven-development/SKILL.md · 当在当前会话中执行包含独立任务的实现计划时使用
v1.0.0 · audit A · 8,494 stars
subagent-driven-development SKILL.md skill
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…
git:20260601.da7723a · audit A · 1,896 stars
subagent-driven-development SKILL.md skill
ganyuanran/aegis · skills/subagent-driven-development/SKILL.md · Use when executing a written implementation plan with independent tasks in the current session where delegation beats…
git:20261011.d34934a · audit A · 1,417 stars
subagent-driven-development SKILL.md skill
mateaix/mateclaw · mateclaw-server/src/main/resources/skills/subagent-driven-development/SKILL.md · Execute plans via delegate_task subagents (2-stage review).
v1.1.0 · audit A · 1,185 stars
subagent-driven-development SKILL.md skill
coco-research/coco · skills/subagent-driven-development/SKILL.md · Use when executing implementation plans with independent tasks in the current session
git:20260802.1479e32 · audit A · 629 stars
subagent-driven-development SKILL.md skill
xu123-bob/baize · agent/skills/superpowers/5.1.0/skills/subagent-driven-development/SKILL.md · Use when executing implementation plans with independent tasks in the current session
git:20260912.5e131e8 · audit A · 617 stars
subagent-driven-development SKILL.md skill
jamditis/claude-skills-journalism · superjawn/skills/subagent-driven-development/SKILL.md · Use when executing implementation plans with independent tasks in the current session
git:20261024.21f0bb2 · audit A · 450 stars

Browse by kind, by grade A, or by owner.