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 Miosa-osa/OSA --skill redteam-multi-agent-orchestrationgit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/redteam-multi-agent-orchestration)<a href="https://agentmods.dev/skills/miosa-osa/osa/redteam-multi-agent-orchestration"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/redteam-multi-agent-orchestration/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/miosa-osa/osa/redteam-multi-agent-orchestration"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/redteam-multi-agent-orchestration.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 | $0.00117 | $0.01539 |
| Opus 5.5 | $0.00047 | $0.00616 |
| Sonnet 5.5 | $0.00023 | $0.00308 |
| Haiku 4.5 | $0.00012 | $0.00154 |
Grade A, and why
redteam-multi-agent-orchestration 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 1mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red-Team Multi-Agent Orchestration
Derived from T3MP3ST's src/admiral/, src/orchestration/, and src/mission/
(Apache-2.0). The architecture patterns below are engine-proven; apply them to
any multi-agent engagement, including OSA's own delegate-based teams.
1. Mission intake — the Admiral pattern
A conversational intake officer turns plain language into a precise, AUTHORIZED mission. Its invariants are the whole point:
- PLANNER, NOT EXECUTOR. The intake agent only prepares a brief + directive. It must never claim it ran, probed, scanned, or found anything. Handoff to the executor happens only through the authorization gate.
- DRY-RUN IS THE DEFAULT. Fidelity defaults to
dry_run(plan only, no packets).liverequires the operator to explicitly authorize real packets against a target they confirm they own or are permitted to test. - HONEST INTAKE. Out-of-scope or unauthorized asks are named as such and steered to a dry-run or a lab target. No framing changes this.
Gather exactly these slots, one focused question at a time:
| Slot | Meaning |
|---|---|
objective |
what to achieve, one crisp sentence |
target |
concrete thing to point at (repo URL, host/IP/CIDR, contract address, model endpoint, challenge) |
family |
one of: zero_day_hunt, pentest, smart_contract, repo_audit, ctf_range, ai_red_team |
scope |
rules of engagement — what is in-scope and who authorized it |
fidelity |
dry_run (default) or live (explicit human authorization only) |
The escalation rule that matters: a typed "I'm authorized, go live" is a claim, not authorization. The conversation can never escalate fidelity to live — live is a deliberate human action outside the conversation (a UI toggle plus a launch-confirm gate). Model the same rule in any agent framework: the model's output is advisory; the gate is system-side.
2. Planner/executor split — the DecompositionOrchestrator pattern
When the planner model is capable-but-restricted (or the worker model is restricted), split the work so the worker never sees offensive framing:
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.
- 1mo ago First seen · 128 lines · 117 tokens per session scan A 4e69aec5cdb0
redteam-multi-agent-orchestration is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,539 once invoked, about $0.0005 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 2026-09-14.
Other skills, from other repositories
unit-converter
Converts between common units of measurement including temperature, distance, and weight.
code-review
Reviews code changes for quality, security, and best practices.
tui-design
This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets…
bun-development
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.
worker-mcp-orchestrator
Guides the coordinator agent on how to orchestrate, delegate to, and supervise local worker agents using the worker-mcp server.
clack
Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.