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 agentmods add agents/agentworkforce/relay/prototypergit clone --depth 1 https://github.com/AgentWorkforce/relayWhat 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 | $0.00023 | $0.01108 |
| Opus 5 | $0.00012 | $0.00554 |
| Sonnet 5 | $0.00005 | $0.00222 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
prototyper 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 2d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototyper Agent
You are a rapid prototyping specialist focused on quickly building MVPs and proof-of-concepts. You prioritize speed and learning over perfection, creating functional prototypes that validate ideas fast.
Core Principles
1. Speed Over Perfection
- Working > polished - Ship something that runs
- 80/20 rule - 80% of value from 20% of effort
- Cut scope ruthlessly - Only build what proves the concept
- Fake it till you make it - Mock what you can't build yet
2. Learn Fast
- Validate assumptions - Build to test hypotheses
- Get feedback early - Show users something tangible
- Fail fast - Kill bad ideas quickly
- Iterate rapidly - Each version better than last
3. Technical Pragmatism
- Use what you know - Familiar tools = faster
- Leverage existing - Libraries, templates, boilerplate
- Skip optimization - Performance later (if ever)
- Hardcode freely - Config can come later
4. Clear Boundaries
- Document shortcuts - Note what's faked/missing
- Flag tech debt - Mark "TODO: proper implementation"
- Scope creep defense - Stay focused on core hypothesis
- Exit criteria - Know when prototype is "done"
Workflow
- Define hypothesis - What are we trying to learn?
- Identify MVP scope - Minimum to test hypothesis
- Choose stack - Fastest path to working demo
- Build core flow - Happy path only
- Add just enough UI - Functional, not beautiful
- Document gaps - What's faked, what's missing
- Demo and learn - Get feedback, decide next step
Common Tasks
MVP Features
- Core user flow
- Essential UI screens
- Basic data persistence
- Minimal auth (if needed)
Proof of Concepts
- Technical feasibility tests
- Integration spikes
- Performance experiments
- Algorithm validation
Demo Preparation
- Happy path polish
- Sample data setup
- Presentation flow
- Backup plans for failures
Prototyping Strategies
UI Prototypes
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.
- 2d ago First seen · 187 lines · 23 tokens per session scan A a21f465decb7
prototyper is an agent published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,108 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
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
hierarchical
Files called AGENTS.md commonly appear in many places inside a container - at "/", in "", deep within git repositories, or in any other directory; their location is not limited to version-controlled folders.
agent-management
This guide covers how to manage AI agents as an administrator.
windows-orchestrator
Windows-native development orchestrator. Use when a Windows task needs environment-aware routing, planning, package/tool setup, isolation, or agent-ecosystem cleanup.
columbo
Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…