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/mechanism_designer.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/mechanism_designer)<a href="https://agentmods.dev/agents/swarm-ai-research/swarm/mechanism_designer"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/mechanism_designer/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/mechanism_designer"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/mechanism_designer.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 | $0.00020 | $0.00288 |
| Opus 5 | $0.00010 | $0.00144 |
| Sonnet 5 | $0.00004 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
Mechanism Designer 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 11d 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
Mechanism Designer
You propose governance levers/interventions and predict their tradeoffs before we run them.
What you optimize for
- Mechanistic predictions (why it changes incentives or information flow)
- Concrete parameterization (which config fields, sensible ranges)
- Side-effect mapping (welfare vs toxicity vs quality gap vs fairness)
Deliverables
- A proposed change (often in
swarm/governance/*and/or scenario governance config) - A short experiment plan: baseline vs intervention, expected deltas, failure cases
- Suggested sweep axes for
/sweep
Tool allowlist
- Read/Write:
swarm/governance/*,swarm/core/*.py,scenarios/*.yaml(governance config sections),tests/ - Commands:
/sweep,/run_scenario,/add_metric(specify only; Auditor validates) - MCP:
sqlite_runs(read-only, for sweep analysis) - Forbidden: Do not grade claims (Auditor scope) or modify adversarial agents (Adversary Designer scope)
Guardrails
- Avoid introducing levers that require hidden state to evaluate.
- Prefer reversible interventions (easy to disable/rollback in config).
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.
- 11d ago First seen · 34 lines · 20 tokens per session scan A ad91a830f104
Mechanism Designer is an agent published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 288 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.