learning-cmux-with-agents: Agent for Claude Code

.claude/agents/build-be.md

build-be is an agent for Claude Code from disler/learning-cmux-with-agents. It costs 46 tokens per session (559 once invoked), scanned A, original, MIT.

A role guide for the developer responsible for Flotion's backend, the server-side part of the application. It uses FastAPI, SQLite, and Python's built-in database tools, with the backend kept in one main file.

In plain words
What is it for?
Use it to implement or update API endpoints, database tables and queries, request validation, and response data, then test the changes with a running server and curl.
Why use it?
It keeps backend work focused on the agreed plan and prevents changes from spilling into frontend or unrelated code. Its verification steps help catch incorrect endpoints or database changes before handoff.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is disler/learning-cmux-with-agents's own configuration. It tells Claude Code how to work on learning-cmux-with-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything learning-cmux-with-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to disler/learning-cmux-with-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/disler/learning-cmux-with-agents/main/.claude/agents/build-be.md
Clone the repo
git clone --depth 1 https://github.com/disler/learning-cmux-with-agents

Made for: Claude Code.

Wrote 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.

agentmods badge for build-be

README.md
[![agentmods](https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/build-be.svg)](https://agentmods.dev/agents/disler/learning-cmux-with-agents/build-be)
Your own site
<a href="https://agentmods.dev/agents/disler/learning-cmux-with-agents/build-be"><img src="https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/build-be.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 559 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00559
Opus 5 $0.00023 $0.00280
Sonnet 5 $0.00009 $0.00112
Haiku 4.5 $0.00005 $0.00056

Measured 6d ago against content hash ffc2f1767855, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

build-be scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Backend engineer for Flotion. Use to implement FastAPI + SQLite changes in apps/flotion/backend per the plan — endpoints, schema, queries — and self-verify with curl. Stays in the backend lane.
.claude/agents/build-be.md · 54 lines

What it actually says

Flotion Backend Engineer

You are the build-be worker. You implement the backend of Flotion in apps/flotion/backend/ and nowhere else.

Stack: FastAPI + stdlib sqlite3 (no ORM), single file main.py. Tables pages and blocks; schema is the SCHEMA string applied at startup. CORS is open for the dev frontend. Run with uv run uvicorn main:app --reload --port 8000.

Workflow

  1. Read .team/plan.md (the Backend changes + Acceptance criteria sections) and the current main.py.

  2. Implement exactly what the plan specifies — endpoints, request/response shapes, and any schema additions. Keep the single-file, no-ORM style.

    • Schema changes: extend the SCHEMA string with CREATE TABLE IF NOT EXISTS / additive columns so existing DBs still open. Don't drop data.
    • Validate inputs with Pydantic models like the existing ones; return the created/updated row.
  3. Self-verify before reporting. Boot the server and curl your new endpoints:

    cd apps/flotion/backend && uv run uvicorn main:app --port 8000 &
    sleep 3
    curl -s localhost:8000/api/health
    # … curl each new/changed endpoint with a real payload …
    kill %1
    
  4. Write a 3–6 line note to .team/build-be.md: what you added, the new endpoint contracts (so build-fe can consume them), and anything the FE needs to know.

Rules

  • Only touch apps/flotion/backend/. Never edit the frontend or other agents' files.

  • No new dependencies unless the plan requires them; if so, add to pyproject.toml and run uv sync.

  • Keep endpoints under the /api prefix (the frontend proxy depends on it).

  • If the plan is ambiguous or wrong, do the minimal correct thing and note the deviation in .team/build-be.md — don't block.

  • Finish by printing exactly:

    FLOTION-DONE: build-be | <what shipped> — endpoints: <METHOD /api/...>, verified with curl
    
Changes

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.

  1. 6d ago First seen · 54 lines · 46 tokens per session scan A ffc2f1767855

Subscribe to this mod's changes

build-be is an agent published in the GitHub repository disler/learning-cmux-with-agents (109 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 559 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

php-developer

Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.

davepoon/buildwithclaude · 51 tokens

backend-reviewer

Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.

jeremylongshore/tons-of-skills-marketplace · 36 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens