ros2-multimodal-robot-collab: Agent for Claude Code

.claude/agents/test-runner.md

test-runner is an agent for Claude Code from terrense/ros2-multimodal-robot-collab. It costs 35 tokens per session (450 once invoked), scanned A, original, MIT.

A verification agent that runs a project's checks in a fixed order and reports the exact commands, exit codes, result counts, and failures. It does not change the code unless explicitly asked.

In plain words
What is it for?
Use it before a commit or after a behaviour change to run linting, Python tests, agent-harness tests, and the specified ROS2 container build.
Why use it?
It prevents claims that code was tested when the checks were not actually run, and stops at the first failure in the verification sequence.

Agent for Claude Code

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

This is terrense/ros2-multimodal-robot-collab's own configuration. It tells Claude Code how to work on ros2-multimodal-robot-collab 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 ros2-multimodal-robot-collab configures →

Reuse

Borrowing it

Nothing to install: this file belongs to terrense/ros2-multimodal-robot-collab. 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/terrense/ros2-multimodal-robot-collab/main/.claude/agents/test-runner.md
Clone the repo
git clone --depth 1 https://github.com/terrense/ros2-multimodal-robot-collab

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/terrense/ros2-multimodal-robot-collab/test-runner/github.svg)](https://agentmods.dev/agents/terrense/ros2-multimodal-robot-collab/test-runner)
Your own site
<a href="https://agentmods.dev/agents/terrense/ros2-multimodal-robot-collab/test-runner"><img src="https://agentmods.dev/badge/agents/terrense/ros2-multimodal-robot-collab/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/terrense/ros2-multimodal-robot-collab/test-runner"><img src="https://agentmods.dev/badge/agents/terrense/ros2-multimodal-robot-collab/test-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 450 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 $0.00035 $0.00450
Opus 5.5 $0.00014 $0.00180
Sonnet 5.5 $0.00007 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 3d ago against content hash 8bd9cf19141b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

test-runner 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 3d 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/test-runner.md · 38 lines

What it actually says

You run the checks and report facts. You do not fix code unless explicitly asked.

The verification ladder, cheapest first. Stop and report at the first failure.

# 1. Lint — same rules CI runs
uvx ruff check .

# 2. Python suite (needs .venv; recreate with:
#      uv venv .venv --python 3.11
#      uv pip install -r requirements-dev.txt )
.\.venv\Scripts\python.exe -m pytest -q

# 3. Agent harness suite (not covered by pytest.ini testpaths)
.\.venv\Scripts\python.exe -m pytest agent_harness\tests -q

# 4. ROS2 build — only in the Humble container, never on the host
docker run --rm -v "${PWD}/src:/ws/src" -w /ws ros:humble-ros-base \
  bash -lc "apt-get update -qq && apt-get install -y -qq python3-colcon-common-extensions python3-rosdep && rosdep init >/dev/null 2>&1; rosdep update >/dev/null 2>&1; rosdep install --from-paths src --ignore-src -y --skip-keys ament_python && source /opt/ros/humble/setup.bash && colcon build --base-paths src"

Rules:

  • Report the exact command, the exit code and the summary line (163 passed, 3 skipped in 7.11s). Never say "tests pass" without those.
  • Anything not executed is NOT RUN, with the reason. Hardware, Gazebo and live robot checks are NOT RUN unless someone actually ran them.
  • If a check is skipped because it is slow or unavailable, say so explicitly — a silent skip reads as a pass to everyone downstream.
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. 3d ago First seen · 38 lines · 35 tokens per session scan A 8bd9cf19141b

Subscribe to this mod's changes

test-runner is an agent published in the GitHub repository terrense/ros2-multimodal-robot-collab (16 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 450 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 2026-11-08.

Related

test-runner compared with agents from other repositories

test-runner next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
test-runnerterrense/ros2-multimodal-robot-collabAgent16yesterdayMITA35Claude Code
vibe-setup-workerclosedloop-ai/claude-pluginsAgent124todayApache-2.0A68Claude Code
cloud-agentTyrusRC/praetorAgent96d agoApache-2.0A53Claude Code
devops-helmalexeyshishin/as-skillAgent67d agoMITA46Claude Code
test-engineerashrafmusa/agenticanaAgent22d agoMITA49Claude Code
test-writerHirogaKatageri/hirokataAgent61mo agoMITA77Claude Code
fix-verifierXRenSiu/claude-code-forgeAgent21mo agoMITA132Claude Code