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 KevinZai/commander --skill ccc-spawngit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-spawn)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-spawn"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-spawn/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/kevinzai/commander/ccc-spawn"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-spawn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.01488 |
| Opus 5.5 | $0.00029 | $0.00595 |
| Sonnet 5.5 | $0.00014 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
ccc-spawn 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-spawn — spawn hub
CC Commander · $ccc-spawn · one entry point that sends a self-contained task to the right spawn mechanism for this surface.
The on-demand counterpart of the automatic isolation nudge (suggest-ticker). This hub offers; nothing spawns without the user's confirmation.
When to use / when not to
- Use for "do this separately so it does not derail here", "fan this out", "chain spec → build → review", or "get an independent expert pass".
- Do not use for trivial work that belongs in this thread, or when two spawns would edit the same files (merge them into one task or sequence them).
- The automatic nudge already runs every turn; this skill is the manual version.
What happens
1. Pick what to spawn
A sub-command skips this picker. Otherwise call AskUserQuestion (Codex: the same question in plain text), best fit first with 🟢:
question: "What do you want to spawn?"
header: "Spawn"
multiSelect: false
options:
- label: "🟢 Isolated task"
description: "One self-contained task with fresh context; this thread keeps going."
- label: "🚀 Parallel fleet"
description: "Fan out across independent files or units at once (hands off to $ccc-fleet)."
- label: "🔄 Cross-session relay"
description: "Chain spec → build → review as hand-off sessions (ask the user to type $ccc-relay)."
- label: "🔬 Expert pass"
description: "One independent reviewer (security, performance, design, …) prompted to refute."
2. Choose the mechanism for the surface
| Choice | Mechanism |
|---|---|
| Isolated task, result needed in this conversation | Agent tool: subagent_type: "fleet-worker" (or general-purpose), run_in_background: true, effort sized to the brief (low mechanical, medium typical, high hard). Add isolation: "worktree" only when the task writes files while this session keeps editing; a read-only task runs without it. |
| Isolated task as its own session | Claude Desktop (Cowork): emit a spawn_task chip, [🟢 Spawn as separate session]. CLI with the opt-in claude-peers broker: /spawn quick <task>. Codex: codex exec --json or codex cloud exec. |
| Parallel fleet | Invoke $ccc-fleet with the Skill tool, passing the task. |
| Cross-session relay | Tell the user to type $ccc-relay with the chain (user-invoked only). |
| Expert pass | Agent tool, read-only, no isolation: subagent_type security-auditor, performance-engineer, designer, reviewer or another matching plugin agent; effort: "high"; prompt it to refute, not confirm. As a separate session: Cowork spawn_task chip scoped to that reviewer, or CLI /spawn expert <domain>. |
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 Changed · -1 lines f00e8d1838b8
- 14d ago Changed · +33 lines · +24 tokens per session 36c3f3b48b3e
- 1mo ago First seen · 81 lines · 48 tokens per session scan A 1fad76e2560f
ccc-spawn is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,488 once invoked, about $0.0003 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
memstack-automation-n8n-workflow-builder
Use this skill when the user says 'n8n workflow', 'build a workflow', 'automation workflow', 'connect services', or needs visual workflow design with node mapping, data transformations, and error handling for n8n. Do NOT use for standalone webhook endpoints or cron jobs.
memstack-automation-cron-scheduler
Use this skill when the user says 'cron job', 'scheduled task', 'run every', 'cron expression', 'recurring job', or needs production-grade scheduled jobs with overlap prevention, monitoring, and structured logging. Do NOT use for n8n workflows or event-driven webhooks.
search-first
A workflow rule for searching for an existing solution before writing new code. It checks the repository, internal mirrors, package registries, connected tools, and GitHub in that order.
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…
debt-ops-metrics
Print a debt-ops health summary from the metrics log, covering registration rate, feedback action rate, ADR creation, and AI-authored share. Use when the user asks for "debt-ops metrics", "debt health", "registry stats", or a tech-debt health summary. Read-only, never writes the log.
knowledgebase
Generate professional multi-page HTML knowledge bases and study guides for software engineering, data science, and AI/ML work — field guides, solution handbooks, service catalogs, team runbooks, onboarding documentation, and technical study resources. Produces self-contained, offline-capable HTML sites with sidebar…