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 krzysztofsurdy/code-virtuoso --skill agent-creatorgit 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/agent-creator)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/agent-creator"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/agent-creator.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 5.1 | $0.00103 | $0.01406 |
| Opus 5 | $0.00051 | $0.00703 |
| Sonnet 5 | $0.00021 | $0.00281 |
| Haiku 4.5 | $0.00010 | $0.00141 |
Grade A, and why
agent-creator 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Creator
Create a sub-agent that earns its context window. Most agents fail not because the model is weak but because the definition is vague - unclear trigger, sprawling tool list, a body that mixes persona and procedure, and no output contract. This skill walks you through a six-phase design so the resulting agent is focused, least-privileged, and predictable.
Core Principles
| Principle | Meaning |
|---|---|
| One job, one agent | An agent that does two things does neither well. Split the responsibility before writing. |
| Least privilege | Grant the smallest tool set that lets the agent finish its job. Read-only by default. |
| Trigger-first description | The description field is the only thing read before delegation. Pack it with keywords and "when to use". |
| Contract over conversation | Define explicit input, process, and output. Agents are not chat sessions. |
| Isolation when writing | If the agent edits files, run it in a worktree so the orchestrator can review before merging. |
| Portable body, platform frontmatter | Keep the system prompt agent-agnostic. Adapt frontmatter fields per target platform. |
Agent vs Skill - Quick Disambiguation
Before creating an agent, confirm it is the right primitive.
| Use a Skill | Use an Agent |
|---|---|
| Reference material (patterns, checklists, schemas) | Work to perform (investigate, review, implement) |
| Loaded into an existing session | Runs in its own context window |
| Passive knowledge | Active actor with tools and a workflow |
| "Where do I learn about X" | "Do X for me and return a result" |
If the answer is reference material, stop and use the skill-creator skill instead. If the answer is work, continue.
Archetype Selection
Agents fall into three archetypes. Pick one before designing.
| Archetype | Scope | Memory | Modifies files | Typical examples |
|---|---|---|---|---|
| Specialist | Single, repeatable task type | Stateless | Rarely (doc writer, implementer) | Investigator, Reviewer, Refactor Scout, Dependency Auditor, Test Gap Analyzer |
| Role | Entire domain of responsibility | Often persistent (project-level) | Dev roles yes, others no | Product Manager, Architect, Backend Dev, QA Engineer, Project Manager |
| Team-Lead | Coordinates multiple workers in parallel | Shared task list | No (delegates) | Orchestrator, release-train lead, review dispatcher |
What ships with it
13 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.
- phases/01-purpose-and-trigger.md 1.5 KB
- phases/02-name-and-identity.md 996 B
- phases/03-capabilities.md 1.5 KB
- phases/04-system-prompt.md 1.3 KB
- phases/05-placement-and-scope.md 1.3 KB
- phases/06-validate-and-write.md 1.4 KB
- references/archetypes.md 8.4 KB
- references/frontmatter-fields.md 6.9 KB
- references/platforms.md 6.0 KB
- references/system-prompts.md 8.6 KB
- references/tool-selection.md 4.8 KB
- references/tuning.md 2.8 KB
- references/validation.md 3.6 KB
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.
- 8d ago First seen · 100 lines · 103 tokens per session scan A a03d629bcd5e
agent-creator is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (21 stars, last pushed 3mo ago), licensed MIT. It adds 103 tokens to every session and 1,406 once invoked, about $0.0005 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).