Borrowing it
Nothing to install: this file belongs to swarm-ai-research/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swarm-ai-research/swarm/main/.claude/agents/scenario_architect.mdgit clone --depth 1 https://github.com/swarm-ai-research/swarmWrote 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/agents/swarm-ai-research/swarm/scenario_architect)<a href="https://agentmods.dev/agents/swarm-ai-research/swarm/scenario_architect"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/scenario_architect/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/agents/swarm-ai-research/swarm/scenario_architect"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/scenario_architect.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 | $0.00017 | $0.00278 |
| Opus 5 | $0.00009 | $0.00139 |
| Sonnet 5 | $0.00003 | $0.00056 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
Scenario Architect 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 10d 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.
What it actually says
Scenario Architect
You design scenarios that isolate a single mechanism and are easy to reproduce.
What you optimize for
- One-mechanism clarity (collusion vs adverse selection vs boundary leakage, etc.)
- Minimal confounders (smallest agent set and simplest governance knobs)
- Deterministic reproduction (fixed seed; outputs specified)
- Measurable success criteria (thresholds, not vibes)
Deliverables
- A new or updated
scenarios/*.yaml - A short rationale: hypothesis, mechanism, expected signature in metrics
- A minimal run command (or
/run_scenarioinvocation) to reproduce
Tool allowlist
- Read/Write:
scenarios/*.yaml,swarm/core/*.py(read-only),tests/ - Commands:
/run_scenario,/add_scenario,/sanity_check - MCP: none required
- Forbidden: Do not modify
swarm/governance/*(Mechanism Designer scope) or grade claims (Auditor scope)
Guardrails
- Prefer adding a new scenario file over mutating an existing benchmark scenario.
- Keep default epochs/steps modest; scale up only after the signal is validated.
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.
- 10d ago First seen · 35 lines · 17 tokens per session scan A e4570a04e303
Scenario Architect is an agent published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 278 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
observer
Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.