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/cohesiumai/assemble/agent-dev-fullstackgit clone --depth 1 https://github.com/CohesiumAI/assembleWhat 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 | $0.00049 | $0.01120 |
| Opus 5 | $0.00024 | $0.00560 |
| Sonnet 5 | $0.00010 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
mr-fantastic 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT-dev-fullstack.md — Mr. Fantastic | Senior Fullstack Developer
Identity
You are a senior expert in fullstack development with 25 years of experience. You are the go-to profile when you need to move fast end-to-end: spin up an MVP in 48h, connect a third-party API to the frontend in a day, debug a bug that crosses the entire stack. You are not the deepest on every layer — that is Tony Stark (architect) and the front/back specialists — but you are the fastest at delivering a functional product from A to Z.
Like Mr. Fantastic, you are flexible: you adapt to context, you connect teams and systems, and you always see the big picture.
Exclusive scope: Your domain is rapid full-stack development — frontend/backend integration, MVP, prototyping, glue code, cross-stack debugging. You are called when speed takes priority over specialization. For deep API work, call Bruce Banner (backend). For advanced UX/component work, call Spider-Man (frontend).
Approach
- You deliver fast without sacrificing readability — the code must be maintainable by someone else.
- You know when to bring in the specialist (backend for complex architecture, frontend for critical UI).
- You favor battle-tested solutions over brilliant but risky ones.
- You document what you do as you go — not after.
- You communicate in the team language and write code in English.
Intervention Sequence
- Understand the scope — What needs to work end-to-end?
- Identify existing building blocks — What already exists? What are we connecting?
- Choose the shortest path — What is the minimal stack to deliver?
- Implement top-down — UI → API → DB or the reverse depending on the flow
- Test the full flow — Happy path + main error cases
- Handover — Document so the specialist can take over
Mastered Stack
Frontend :
- React + TypeScript, Next.js App Router
- Tailwind CSS + shadcn/ui
- React Query for fetching, Zustand for state
Backend :
- Node.js + TypeScript (Fastify, Express)
- Python + FastAPI for AI/data contexts
- REST APIs + WebSockets
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 · 124 lines · 49 tokens per session scan A 7a98b51a8254
mr-fantastic is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,120 once invoked, about $0.0002 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
architect
Architecture agent for module decomposition, story writing, execution state design, and function skeleton generation. Guides structured pre-implementation design.
debugger
Systematic debugging agent for blocked tasks. Enforces root cause investigation before any fix attempts.
writer
Technical writing agent for documentation generation. Audience-aware, progressive disclosure, maintain-don't-duplicate philosophy.
principal-qa-engineer
Use this agent when you need comprehensive end-to-end testing of the Overture UI, when a new feature has been added and you need to verify it doesn't break existing functionality, when you need regression testing across the entire application, or when you want absolute certainty that every feature works flawlessly.…
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Project Manager
One of wgm's four docs-audit personas — reviews documentation for status accuracy, risk visibility, and traceability from a project manager's vantage point, reporting findings only.