orchestrate

orchestrate is a command for Claude Code from jaskaranhundal/usap-skills. It costs 52 tokens per session (1,616 once invoked), scanned A, original, Apache-2.0.

A command that runs four cybersecurity specialists in sequence on one large incident scenario, passing each specialist's output to the next.

In plain words
What is it for?
Use it to test handoffs between alert triage, incident response, executive advice, and security-program planning, then compare the chain with an expected mock result.
Why use it?
It shows how separate security roles coordinate during a complex incident instead of producing disconnected analyses.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the usap-skills plugin — 87 skills, 7 commands, 1 plugin shipped together

Good fit Use it to test handoffs between alert triage, incident response, executive advice, and security-program planning, then compare the chain with an expected mock result.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jaskaranhundal/usap-skills/orchestrate
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jaskaranhundal/usap-skills

Made for: Claude Code.

Or install usap-skills, the plugin that ships this one along with the rest of its 87 skills, 7 commands, 1 plugin.

Wrote 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.

agentmods badge for orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/orchestrate/github.svg)](https://agentmods.dev/commands/jaskaranhundal/usap-skills/orchestrate)
Your own site
<a href="https://agentmods.dev/commands/jaskaranhundal/usap-skills/orchestrate"><img src="https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/orchestrate/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.

agentmods 80×15 button for orchestrate

Your own site · 80×15
<a href="https://agentmods.dev/commands/jaskaranhundal/usap-skills/orchestrate"><img src="https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01616
Opus 5 $0.00026 $0.00808
Sonnet 5 $0.00010 $0.00323
Haiku 4.5 $0.00005 $0.00162

Measured 9d ago against content hash 3767f79723e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orchestrate 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 9d 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.

.claude/commands/usap/orchestrate.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the full USAP 4-agent orchestration chain against the Perfect Storm scenario.

Read tests/scenarios/nation-state-apt-crisis.json now — you will use it throughout. Read tests/mocks/orchestration-chain-mock.json now — you will compare against it at the end.

Operate each agent in sequence. Each agent reads its own file, adopts its persona, applies its workflow, and produces output that the next agent consumes. Show a clear separator between each agent's section.


Agent 1 of 4 — cs-security-analyst (AT Workflow)

Read agents/security/cs-security-analyst.md in full.

Adopt the Alex persona (Tier 2 SOC, 12y). Apply the AT (Alert Triage) workflow to the Perfect Storm scenario.

Produce abbreviated output focused on the handoff payload:

  • Top-5 alert priority signals (ranked, DDoS noise suppressed)
  • Kill chain stage mapping (6 stages, all 8 vectors assigned)
  • Two threat actor entries (nation-state APT + ransomware gang, clearly differentiated)
  • SEV-1 declaration
  • Routing decision: next_agents: ["cs-incident-responder", "cs-ciso-advisor"] with justification
  • Prerequisite checks: all 7 UNKNOWN fields as PREREQUISITE_UNVERIFIED
  • Sequenced containment plan (ransomware → APT → insider → supply chain)
  • Regulatory flags (GDPR 72h + SEC 4-day)
  • human_approval_required: true

Show the handoff payload passed to Agent 2 (the fields cs-incident-responder will consume).


Agent 2 of 4 — cs-incident-responder (CO Workflow)

Read agents/security/cs-incident-responder.md in full.

Adopt the Jordan persona (IR Lead, 14y). Consume the Agent 1 handoff payload as your incident input.

Apply the CO (Active Containment) workflow. Produce:

  • Formal SEV-1 incident declaration with incident ID and timestamp
  • SLA clock: detection-to-containment target, eradication target, recovery target
  • Containment action intents in correct sequence (ransomware first — all as intent blocks, no CLI)
  • Evidence preservation order: collect C2 artifacts from DC-002 BEFORE evicting APT implants
  • Forensic collection plan for compromised hosts (intent blocks only)
  • Inherited prerequisite checks — propagate all 7 UNKNOWN fields, do not resolve by assumption
  • Rollback plan for each isolation action

Read the full file on GitHub · 139 lines

Changes

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.

  1. 9d ago First seen · 139 lines · 52 tokens per session scan A 3767f79723e1

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository jaskaranhundal/usap-skills (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,616 once invoked, about $0.0003 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 2026-08-31.