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 Bbeierle12/Skill-MCP-Claude --skill subagent-driven-developmentgit clone --depth 1 https://github.com/Bbeierle12/Skill-MCP-ClaudeWrote 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/bbeierle12/skill-mcp-claude/subagent-driven-development)<a href="https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/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/bbeierle12/skill-mcp-claude/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 168 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00031 | $0.00864 |
| Opus 5 | $0.00015 | $0.00432 |
| Sonnet 5 | $0.00006 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00086 |
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 9d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development
Core Principle
Fresh context per task. Review between tasks.
Each task gets a clean subagent with no accumulated confusion. You review between tasks.
How It Works
- Load the implementation plan
- For each task:
- Dispatch fresh subagent
- Subagent implements ONLY that task
- Review the changes
- Approve or request fixes
- Move to next task
Benefits
- Clean Context: Each subagent starts fresh
- Focused Work: One task at a time
- Review Points: Catch issues early
- Controlled Progress: You stay in charge
Execution Flow
Step 1: Load the Plan
Loading plan from: docs/plans/YYYY-MM-DD-feature-name.md
Tasks identified:
1. [ ] Task 1: Description
2. [ ] Task 2: Description
3. [ ] Task 3: Description
Starting with Task 1...
Step 2: Dispatch Subagent
For each task, create a focused prompt:
## Task: [Task Name]
### Context
- Project: [brief description]
- Current branch: [branch name]
- Dependencies: [relevant info]
### Instructions
[Exact instructions from plan]
### Files to Modify
- `path/to/file.ts`
### Test to Write First
[Test code from plan]
### Implementation
[Implementation code from plan]
### Success Criteria
- [ ] Test passes
- [ ] No other tests broken
- [ ] Code follows project style
Step 3: Review Changes
After subagent completes:
## Task 1 Complete
### Changes Made:
- Modified: `path/to/file.ts` (+25/-3)
- Added: `path/to/file.test.ts` (+40)
### Test Results:
✅ All tests passing (47 total)
### Review Checklist:
- [ ] Test covers the requirement
- [ ] Implementation is correct
- [ ] No unnecessary changes
- [ ] Code style matches project
**Approve and continue to Task 2?**
Step 4: Handle Issues
If review finds problems:
## Issues Found in Task 1
1. Test doesn't cover edge case X
2. Missing error handling for Y
**Options:**
A) Request fixes from subagent
B) Fix manually
C) Skip and note for later
Which approach?
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.
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.
- 9d ago First seen · 181 lines · 31 tokens per session scan A 297ab770561b
subagent-driven-development is a skill published in the GitHub repository Bbeierle12/Skill-MCP-Claude (8 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 864 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
aip-tracker
Track Airflow Improvement Proposal (AIP) implementation progress by comparing Confluence specs against codebase evidence. Use when asked to assess, report on, or compare AIP status.
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, or (6) Perform any GitHub…
workspace
Dynamic multi-repo and monorepo awareness for Claude Code. Analyze workspace topology, track API contracts, and maintain cross-repo context.
ticket-craft
Create Jira/Asana/Linear tickets optimized for Claude Code execution - AI-native ticket writing.
team-coordination
Multi-person projects - shared state, todo claiming, handoffs.