redteam-multi-agent-orchestration skillA
redteam-multi-agent-orchestration is agent-read markdown (skill) from miosa-osa/osa: Multi-agent red-team campaign orchestration: mission intake with authorization gates, planner/executor separation, objective decomposition into innocuous worker queries, strict-majority verdict adjudication with mandatory cite-checks, and crash-safe mission recovery with idempotent actions. Use when coordinating multiple agents on an offensive-security engagement, structuring a red-team campaign across specialist operators, designing planner-worker splits for restricted models, or building recov.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# 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). `live` requires 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 | …
Read the whole file at its exact version.
How to install
mdr add miosa-osa/osa/redteam-multi-agent-orchestration@git:20260913.e13b6b8mdr add miosa-osa/osa/redteam-multi-agent-orchestration@sha256:4e69aec5cdb094faPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_jd7hmxk272d5qx67)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6551 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
miosa-osa/osa · 74 stars · license NOASSERTION · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jd7hmxk272d5qx67 GET https://markdownregistry.com/api/v1/resolve?ref=miosa-osa/osa/redteam-multi-agent-orchestration GET https://markdownregistry.com/api/v1/blob/4e69aec5cdb094fa0dd4c13ba4eec14180097887996c13fe4af0cb089b3f22e3
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.