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.
npx skills add brain-bootstrap/claude-code-brain-bootstrap --skill subagent-driven-developmentgit clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrapWrote 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.
[](https://agentmods.dev/skills/brain-bootstrap/claude-code-brain-bootstrap/subagent-driven-development)<a href="https://agentmods.dev/skills/brain-bootstrap/claude-code-brain-bootstrap/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/brain-bootstrap/claude-code-brain-bootstrap/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.
<a href="https://agentmods.dev/skills/brain-bootstrap/claude-code-brain-bootstrap/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/brain-bootstrap/claude-code-brain-bootstrap/subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01184 |
| Opus 5.5 | $0.00013 | $0.00474 |
| Sonnet 5.5 | $0.00007 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00118 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development
Execute a plan by dispatching a fresh subagent per task, with two-stage review after each: spec compliance first, then code quality.
Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.
Why subagents: Isolated context per task — subagents never inherit your session history. You construct exactly what they need. This keeps the coordinator context clean for orchestration work.
When to Use
Use this after /squad-plan generates a parallel workstream plan, OR when you have any plan document with independent tasks.
vs. dispatching subagents manually: This enforces the two-stage review loop automatically — no skipping spec compliance to jump to quality.
Not suitable when tasks are tightly coupled — if task B depends on task A's exact output, execute sequentially in the main context instead.
The Process
Setup:
- Read plan file once — extract ALL tasks with full text and context
- Create tasks in
claude/tasks/todo.mdwith all task titles
Per task loop:
- Dispatch implementer subagent with: full task text + relevant file context (do NOT make subagent read the plan — provide it directly)
- If subagent asks questions → answer completely before letting them proceed
- Implementer implements, tests, commits, self-reviews → reports status
- Dispatch spec compliance reviewer (bootstrap
reviewersubagent type) → does code match the spec?- Issues found → implementer fixes → spec reviewer re-reviews → repeat until ✅
- Dispatch code quality reviewer (bootstrap
reviewersubagent type) → is code clean, tested, production-ready?- Issues found → implementer fixes → quality reviewer re-reviews → repeat until ✅
- Mark task complete in
claude/tasks/todo.md
After all tasks:
- Dispatch final reviewer across entire implementation
- Run
/mrto finalize the branch
Handling Implementer Status
| Status | Action |
|---|---|
DONE |
Proceed to spec compliance review |
DONE_WITH_CONCERNS |
Read concerns first — address correctness/scope concerns before review, note observations and proceed |
NEEDS_CONTEXT |
Provide missing context, re-dispatch |
BLOCKED |
Diagnose: context problem → provide context + re-dispatch; needs more reasoning → re-dispatch with opus model; task too large → break into smaller pieces; plan is wrong → escalate to user |
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.
- 1mo ago First seen · 137 lines · 33 tokens per session scan A 1f1d678b41c5
subagent-driven-development is a skill published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 1,184 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
review-spec
Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.
review-design
Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.
review-architecture
Review a written architecture artifact — an ADR (docs/adr/), a broader architecture doc, the architecture section of a design doc, or a domain-reference kit (glossary + traps pages, reviewed as one composite artifact) — against the system it claims to describe. Verifies the EXISTENCE and TOPOLOGY of declared…
review-code
Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.
diff-skill
Compare two versions of a skill's instructions to detect degradations and complexity increases. TRIGGER when: user asks to diff, compare, or review changes to a skill's markdown instructions. Asymmetric check — only regressions count. Additions, clarifications, and strengthenings are not degradations. Compares HEAD →…
greet
Ask for the user's preferred name before greeting.