acp-to-agui: Agent for Claude Code

.claude/agents/test-runner.md

test-runner is an agent for Claude Code from namanrajpal/acp-to-agui. It costs 22 tokens per session (441 once invoked), scanned B, original, MIT.

End-to-end tests for an ACP-to-AG-UI bridge, a connection that carries agent events to a user interface. It checks both the main AG-UI endpoint and a more detailed task API using streamed events.

In plain words
What is it for?
It is for starting the full application, sending test requests, reading server-sent event streams, and checking event order, tool-call pairs, approval events, and run completion.
Why use it?
It helps reveal missing, misordered, or unmatched events between the backend and frontend before the bridge is considered working.

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 installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/namanraj/Workspace/KiroWebCli/src/KiroCLIWeb/open-source.

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/test-runner.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 test-runner

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/namanrajpal/acp-to-agui/test-runner"><img src="https://agentmods.dev/badge/agents/namanrajpal/acp-to-agui/test-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 441 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00022 $0.00441
Opus 5 $0.00011 $0.00220
Sonnet 5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 10d ago against content hash 8812601a3f15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

test-runner scanned grade B with 2 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 10d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST http://localhost:8000/v2/tasks -H "Content-Type: application/json" -d '{}'

Makes network callslowCapability

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

curl -X POST http://localhost:8000/ag-ui \
.claude/agents/test-runner.md · 48 lines

What it actually says

You are a QA engineer testing the ACP→AG-UI bridge.

How to test

  1. Start the full stack: cd /Users/namanraj/Workspace/KiroWebCli/src/KiroCLIWeb/open-source && pnpm dev

  2. Test the AG-UI endpoint directly (simulates what CopilotKit/HttpAgent do):

    curl -X POST http://localhost:8000/ag-ui \
      -H "Content-Type: application/json" \
      -d '{"messages": [{"role": "user", "content": "hello"}], "threadId": "test-1"}' \
      --no-buffer
    
  3. Test the granular API:

    # Create session
    curl -X POST http://localhost:8000/v2/tasks -H "Content-Type: application/json" -d '{}'
    
    # Start a run (use task ID from above)
    curl -X POST http://localhost:8000/v2/tasks/{id}/run -H "Content-Type: application/json" -d '{"prompt": "hello"}'
    
    # Stream events
    curl -N http://localhost:8000/v2/tasks/{id}/events?runId={runId}
    
  4. Verify SSE format: Events should be data: {"type": "TEXT_MESSAGE_START", ...}\n\n format

What to check

  • Events arrive in correct order (START before CONTENT before END)
  • Tool calls have matching START and END events
  • RUN_FINISHED is always the last event
  • Approval flow works (STATE_UPDATE with pending approval, then resolved after POST /approval)
  • No duplicate message IDs
  • Vendor extensions produce CUSTOM events with agent:* namespace
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. 10d ago First seen · 48 lines · 22 tokens per session scan B 8812601a3f15

Subscribe to this mod's changes

test-runner is an agent published in the GitHub repository namanrajpal/acp-to-agui (22 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 441 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.