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 agentmods add skills/opensesh/karimo-overview/subagent-driven-developmentnpx skills add opensesh/karimo-overview --skill subagent-driven-developmentgit clone --depth 1 https://github.com/opensesh/karimo-overviewWrote 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/opensesh/karimo-overview/subagent-driven-development)<a href="https://agentmods.dev/skills/opensesh/karimo-overview/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/opensesh/karimo-overview/subagent-driven-development.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01848 |
| Opus 5 | $0.00000 | $0.00924 |
| Sonnet 5 | $0.00000 | $0.00370 |
| Haiku 4.5 | $0.00000 | $0.00185 |
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 yesterday.
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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development
This skill activates when executing implementation plans, handling multi-task work, or when parallel execution would be beneficial. Triggers on phrases like "implement the plan", "execute tasks", "dispatch agents", or when more than 3 independent tasks exist.
Core Concept
Execute implementation plans by dispatching independent subagents for each task, with mandatory two-stage reviews: spec compliance first, then code quality.
Fresh agent per task + BOS-aware reviews = high quality, fast iteration
When to Use
Apply this approach when you have:
- A completed implementation plan (see: writing-plans skill)
- Tasks that are mostly independent
- Intent to work in parallel within one session
Decision Tree:
Have an implementation plan?
├── No → Use writing-plans skill first
└── Yes → Are tasks independent?
├── No → Execute sequentially
└── Yes → Use subagent-driven development ✓
Process Flow
1. Preparation
Extract all tasks from plan into a tracking list:
## Task List
- [ ] Task 1: Create component skeleton
- [ ] Task 2: Implement core logic
- [ ] Task 3: Add styling with BOS tokens
- [ ] Task 4: Write integration tests
2. Per-Task Cycle
For each task:
┌─────────────────────────────────────────────────────────────────┐
│ DISPATCH IMPLEMENTER │
│ → Use implementer-prompt with full task context │
│ → Include BOS design system requirements │
└─────────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────────┐
│ ANSWER QUESTIONS │
│ → Clarify requirements before work begins │
│ → Provide BOS pattern references if needed │
└─────────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────────┐
│ SPEC COMPLIANCE REVIEW │
│ → Did they build exactly what was requested? │
│ → Missing requirements? Extra features? │
│ → BOS tokens used correctly? │
└─────────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────────┐
│ CODE QUALITY REVIEW │
│ → Clean, tested, maintainable? │
│ → React Aria patterns followed? │
│ → Design system compliance verified? │
└─────────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────────┐
│ ITERATE IF ISSUES │
│ → Fix flagged issues │
│ → Re-review until approved │
└─────────────────────────────────────────────────────────────────┘
↓
Mark task complete, proceed to next
What ships with it
2 files 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.
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.
- yesterday First seen · 340 lines · 0 tokens per session scan A df7639875bde
subagent-driven-development is a skill published in the GitHub repository opensesh/karimo-overview (11 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,848 tokens. 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
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
mcporter
Discover and call MCP Server tools via the mcporter CLI. Use when your coordinator notifies you about new MCP tools, or when you need to call external APIs. Includes workflow for generating skill documentation for new MCP servers.
task-management
Use before any Worker taskflow call or assigned-task workflow, including reading task state, acknowledging a task, executing a task, tracking progress, handling blockers/questions, submitting structured results, or reporting completion. Always use this skill when the message mentions assigned task, task ID…
task-coordination
Coordinate access to shared task directories using .processing marker files. Use before accessing a Worker's workspace to prevent conflicts when both Manager and Worker might modify files simultaneously.
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…
investigate
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…