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.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osWrote 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/commands/frankxai/agentic-creator-os/acos-swarm)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/acos-swarm"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/acos-swarm/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/commands/frankxai/agentic-creator-os/acos-swarm"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/acos-swarm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00457 |
| Opus 5 | $0.00000 | $0.00229 |
| Sonnet 5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
acos-swarm 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 6d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACOS Swarm - Multi-Agent Orchestration
Initialize a coordinated swarm of agents for complex, multi-file tasks.
When to Use
Auto-invoke swarm when the task involves:
- 3+ files changing
- New feature implementation
- Cross-module refactoring
- Full-stack changes (frontend + backend + tests)
- Performance optimization across multiple areas
Anti-Drift Configuration (Default)
Use hierarchical topology with specialized strategy for maximum coherence:
Topology: hierarchical (coordinator validates each output)
Max Agents: 6-8 (smaller team = less drift)
Strategy: specialized (clear roles, no overlap)
Swarm Patterns
Feature Development (Most Common)
Spawn these agents concurrently using the Task tool:
- Researcher - Analyze requirements and existing code patterns
- Architect - Design implementation approach
- Coder - Implement the solution
- Tester - Write tests
- Reviewer - Review code quality
Bug Fix
- Researcher - Reproduce and trace the bug
- Coder - Implement the fix
- Tester - Write regression test
Content Pipeline
- Researcher - Research topic and keywords
- Writer - Draft content
- SEO Specialist - Optimize for search
- Designer - Create visual assets
Deployment
- Validator - Pre-deploy checks
- Deployer - Sync and push to production
- Monitor - Verify deployment success
Execution
When this command is invoked:
- Identify the task type from user's request
- Select the appropriate swarm pattern above
- Spawn ALL agents concurrently in ONE message using Task tool
- Each agent gets clear, non-overlapping instructions
- Create checkpoints after each agent completes
- Swarm hooks track communication between agents
CLI Alternative
npx claude-flow@v3alpha swarm init --topology hierarchical --max-agents 8 --strategy specialized
Remember: Claude Code's Task tool does the ACTUAL work. Swarm coordination is about organizing the work efficiently.
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.
- 6d ago First seen · 74 lines · 0 tokens per session scan A 229d4b327179
acos-swarm is a command published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 457 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 commands, from other repositories
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
pre-mortem
Run a pre-mortem risk analysis on a PRD, launch plan, or feature — identify what could go wrong before it does.
stakeholder-map
Map stakeholders on a Power × Interest grid and create a tailored communication plan.
write-prd
Create a comprehensive Product Requirements Document from a feature idea or problem statement.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
retro
Facilitate a post-launch or sprint retrospective anchored to OKRs.