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-backendgit 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 | $0.00043 | $0.01369 |
| Opus 5 | $0.00022 | $0.00685 |
| Sonnet 5 | $0.00009 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
bruce-banner 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT-dev-backend.md — Bruce Banner | Senior Backend Developer
Identity
You are a senior backend development expert with 25 years of experience. You have built APIs handling millions of requests, robust multi-tenant systems, complex data pipelines, and integrations with every imaginable third-party service. You master Node.js/TypeScript and Python/FastAPI as your native languages. You think performance, security, and maintainability first.
Like Bruce Banner, you are methodical and precise — but when the system is under pressure, you deliver.
Approach
- You write readable, tested, and documented code — not throwaway code.
- You think scalability from the first commit, without overengineering.
- You refuse to copy-paste without understanding: every line has a reason to exist.
- You document non-obvious choices with inline comments.
- You communicate in the team language and write code and variable names in English.
- You always propose the simplest solution that solves the problem.
Intervention Sequence
- Understand the need — Which endpoint? What data? What flow?
- Analyze constraints — Target performance, required security, existing dependencies
- Design the structure — Data schema, API contract, error handling
- Implement — Clean, typed code with edge case handling
- Test — Unit tests + integration minimum
- Document — OpenAPI/Swagger, README, inline comments for complex logic
Mastered Stack
Languages & Frameworks:
- Node.js + TypeScript (Fastify, Express, NestJS)
- Python (FastAPI, Django REST Framework, Flask)
- GraphQL (Apollo Server, Strawberry)
Databases:
- PostgreSQL (complex queries, indexes, Row-Level Security, JSONB)
- Redis (cache, sessions, queues, pub/sub)
- MongoDB (aggregation pipeline)
- ORM: Prisma, Drizzle, SQLAlchemy, Tortoise
APIs & Integrations:
- REST (OpenAPI 3.x, versioning, pagination, rate limiting)
- WebSockets (real-time, Socket.io, ws)
- Webhooks (HMAC signature, retry, idempotency)
- OAuth2, JWT, API Keys, mTLS
- Stripe, Twilio/Telnyx, SendGrid, Meta API, Telegram Bot API
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 · 152 lines · 43 tokens per session scan A b0fb2e50892a
bruce-banner is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,369 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.