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/krzysztofsurdy/code-virtuoso/subagent-driven-developmentnpx skills add krzysztofsurdy/code-virtuoso --skill subagent-driven-developmentgit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/subagent-driven-development)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/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 | $0.00163 | $0.03174 |
| Opus 5 | $0.00081 | $0.01587 |
| Sonnet 5 | $0.00033 | $0.00635 |
| Haiku 4.5 | $0.00016 | $0.00317 |
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 5d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development
An orchestration pattern for executing multi-task implementation plans by dispatching one fresh subagent per task, reviewing each task through two gates (spec compliance, then code quality), and advancing only after both gates pass. The orchestrator stays lean - it coordinates, briefs, reviews, and hands off. It never implements.
Core Principles
| Principle | Meaning |
|---|---|
| One fresh agent per task | Each task gets a new subagent with curated context. No inherited conversation history, no accumulated drift. The agent sees only what the brief provides. |
| Two-stage review | Every task passes through spec compliance (does it match the brief?) and then code quality (is it correct, clean, and tested?). Both must pass before advancing. |
| Structured hand-offs | When task N produces artifacts that task N+1 needs, pass a compressed summary (diff, test manifest, notes) - never raw conversation history. |
| Orchestrator stays lean | The orchestrator reads the plan, dispatches agents, reviews output, and decides next steps. It does not implement, debug, or accumulate working-memory bloat. |
| Fail fast, fix forward | When a review gate fails, return specific feedback to the subagent for a focused fix cycle. After two failed fix attempts, re-scope or escalate - do not loop indefinitely. |
When to Use
| Situation | Why this pattern fits |
|---|---|
| Written plan with 3+ sequential tasks | Each task benefits from isolated execution and a review checkpoint |
| Tasks that build on each other (feature branches, migrations) | Structured hand-offs prevent context corruption between steps |
| Long implementation sessions that risk context exhaustion | Fresh agents per task keep each execution window small and precise |
| Quality-sensitive work requiring audit trails | Two-stage review produces documented accept/reject decisions per task |
| Delegating to less capable models for mechanical work | Tight briefs and review gates compensate for reduced reasoning capacity |
What ships with it
4 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.
- 5d ago First seen · 261 lines · 163 tokens per session scan A 4a13febef2fa
subagent-driven-development is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (20 stars, last pushed 3mo ago), licensed MIT. It adds 163 tokens to every session and 3,174 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
instruction-eval
Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use…
worth-building
Decide how elaborate to build something (simple vs. robust) and return a concrete, PoC-shaped proposal at that level — not over- or under-engineered, but right-sized. Use whenever someone is building something and the investment level is unclear: "quick or proper?", "MVP vs. real product", "is this over-engineering?"…
django-ticket-triage
Analyze a Django Trac ticket and produce a triage recommendation report — duplicate search, related PRs, forum threads, and the affected source code. Use when the user gives a Django ticket number, or asks whether a ticket is valid, a duplicate, or ready for a triage stage.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).