agentmods.dev

acp-to-agui: Agent for Claude Code

.claude/agents/backend-dev.md

backend-dev is an agent for Claude Code from namanrajpal/acp-to-agui. It costs 21 tokens per session (419 once invoked), scanned A, original, MIT.

An agent for developing the Python FastAPI backend of a bridge between the Agent Client Protocol and AG-UI, a user-interface event format for agents.

In plain words
What is it for?
Working on agent process management, ACP message handling, conversion to AG-UI events, server-sent event streaming, sessions, REST endpoints, configuration, and tool approval rules.
Why use it?
It gives backend work a defined map of the project's session, subprocess, event-translation, streaming, and permission components.

Agent for Claude Code

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

This is namanrajpal/acp-to-agui's own configuration. It tells Claude Code how to work on acp-to-agui 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 acp-to-agui configures →

not rated 23repo +1 5mo ago A scan 21 tokens original MIT
View source ↗ namanrajpal/acp-to-agui
Reuse

Borrowing it

Nothing to install: this file belongs to namanrajpal/acp-to-agui. 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/namanrajpal/acp-to-agui/main/.claude/agents/backend-dev.md
Clone the repo
git clone --depth 1 https://github.com/namanrajpal/acp-to-agui

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 backend-dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/namanrajpal/acp-to-agui/backend-dev/github.svg)](https://agentmods.dev/agents/namanrajpal/acp-to-agui/backend-dev)
Your own site
<a href="https://agentmods.dev/agents/namanrajpal/acp-to-agui/backend-dev"><img src="https://agentmods.dev/badge/agents/namanrajpal/acp-to-agui/backend-dev/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.

agentmods 80×15 button for backend-dev

Your own site · 80×15
<a href="https://agentmods.dev/agents/namanrajpal/acp-to-agui/backend-dev"><img src="https://agentmods.dev/badge/agents/namanrajpal/acp-to-agui/backend-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00021 $0.00419
Opus 5.5 $0.00008 $0.00168
Sonnet 5.5 $0.00004 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 2mo ago against content hash b4f145c2edf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

backend-dev 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 2mo 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.

.claude/agents/backend-dev.md · 41 lines

What it actually says

You are a backend developer working on the ACP→AG-UI bridge's Python/FastAPI layer.

Project structure

  • backend/main.py — FastAPI app setup, CORS, router mounting
  • backend/agent/runner.py — Spawns ACP agent subprocess, manages lifecycle
  • backend/agent/acp_protocol.py — ACP SDK integration (JSON-RPC over stdio)
  • backend/bridge/acp_to_agui.py — Core translation: ACP notifications → AG-UI events
  • backend/agui/events.py — AG-UI event type definitions
  • backend/agui/sse.py — SSE stream encoding
  • backend/sessions/manager.py — Session lifecycle orchestration
  • backend/sessions/store.py — In-memory session store
  • backend/sessions/routes.py — REST API endpoints
  • backend/policy/tool_policy.py — Tool approval rules
  • backend/agui_endpoint.py — Standard POST /ag-ui endpoint
  • backend/config.py — Reads bridge.config.json

Key patterns

  • The bridge uses asyncio.Future to bridge synchronous ACP request_permission() callbacks with async REST approval endpoints
  • Message boundary tracking: the bridge maintains state about open text messages and pending tool calls
  • Vendor extensions from ACP (_vendor.dev/*) are normalized to CUSTOM AG-UI events in agent:* namespace
  • Config comes from bridge.config.json at project root

When implementing

  • Use Python 3.11+ features
  • Follow existing patterns (Pydantic models, async/await, FastAPI dependency injection)
  • Run with pnpm dev:backend or uvicorn backend.main:app --reload --port 8000
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. 2mo ago First seen · 41 lines · 21 tokens per session scan A b4f145c2edf4

Subscribe to this mod's changes

backend-dev is an agent published in the GitHub repository namanrajpal/acp-to-agui (23 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 419 once invoked, about $0.0001 per session on Opus 5.5. 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.

Backend and APIsacpacp-protocolagentaguibridgebridge-sdk
Related

backend-dev compared with agents from other repositories

backend-dev next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
backend-devnamanrajpal/acp-to-aguiAgent235mo agoMITA21Claude Code
integratorAgentWorkforce/relayAgent1.1kyesterdayApache-2.0A23Claude Code
api-designerAgentWorkforce/relayAgent1.1kyesterdayApache-2.0A35Claude Code
rust-framework-architecteunomia-bpf/agentsightAgent7756d agoMITA0Claude Code
java-proechoVic/blade-codeAgent18124d agoMITA44Claude Code
api-documenterechoVic/blade-codeAgent18124d agoMITA43Claude Code
architectalvin-reyes/better-agentic-ideAgent452d agoMITA36Claude Code