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 skills add arpitg1304/robotics-agent-skills --skill ros1git clone --depth 1 https://github.com/arpitg1304/robotics-agent-skillsWrote 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.
[](https://agentmods.dev/skills/arpitg1304/robotics-agent-skills/ros1)<a href="https://agentmods.dev/skills/arpitg1304/robotics-agent-skills/ros1"><img src="https://agentmods.dev/badge/skills/arpitg1304/robotics-agent-skills/ros1/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.
<a href="https://agentmods.dev/skills/arpitg1304/robotics-agent-skills/ros1"><img src="https://agentmods.dev/badge/skills/arpitg1304/robotics-agent-skills/ros1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 127 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00138 | $0.03224 |
| Opus 5 | $0.00069 | $0.01612 |
| Sonnet 5 | $0.00028 | $0.00645 |
| Haiku 4.5 | $0.00014 | $0.00322 |
Grade A, and why
ros1 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 12d 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 — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROS1 Development Skill
When to Use This Skill
- Building or maintaining ROS1 packages and nodes
- Writing launch files, message types, or services
- Debugging ROS1 communication (topics, services, actions)
- Configuring catkin workspaces and build systems
- Working with tf/tf2 transforms, URDF, or robot models
- Using actionlib for long-running tasks
- Optimizing nodelets for zero-copy transport
- Planning ROS1 → ROS2 migration
Core Architecture Principles
1. Node Design
Single Responsibility Nodes: Each node should do ONE thing well. Resist the temptation to build monolithic "do-everything" nodes.
# BAD: Monolithic node
class RobotNode:
def __init__(self):
self.sub_camera = rospy.Subscriber('/camera/image', Image, self.camera_cb)
self.sub_lidar = rospy.Subscriber('/lidar/points', PointCloud2, self.lidar_cb)
self.pub_cmd = rospy.Publisher('/cmd_vel', Twist, queue_size=10)
self.pub_map = rospy.Publisher('/map', OccupancyGrid, queue_size=1)
# This node does perception, planning, AND control
# GOOD: Decomposed nodes
class PerceptionNode: # Fuses sensor data → publishes /obstacles
class PlannerNode: # Subscribes /obstacles → publishes /path
class ControllerNode: # Subscribes /path → publishes /cmd_vel
Node Initialization Pattern:
#!/usr/bin/env python
import rospy
from std_msgs.msg import String
class MyNode:
def __init__(self):
rospy.init_node('my_node', anonymous=False)
# 1. Load parameters FIRST
self.rate = rospy.get_param('~rate', 10.0)
self.frame_id = rospy.get_param('~frame_id', 'base_link')
# 2. Set up publishers BEFORE subscribers
# (prevents callbacks firing before publisher is ready)
self.pub = rospy.Publisher('~output', String, queue_size=10)
# 3. Set up subscribers LAST
self.sub = rospy.Subscriber('~input', String, self.callback)
rospy.loginfo(f"[{rospy.get_name()}] Initialized with rate={self.rate}")
def callback(self, msg):
# Process and republish
result = String(data=msg.data.upper())
self.pub.publish(result)
def run(self):
rate = rospy.Rate(self.rate)
while not rospy.is_shutdown():
# Periodic work here
rate.sleep()
if __name__ == '__main__':
try:
node = MyNode()
node.run()
except rospy.ROSInterruptException:
pass
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.
- 12d ago First seen · 408 lines · 138 tokens per session scan A f415dea88564
ros1 is a skill published in the GitHub repository arpitg1304/robotics-agent-skills (356 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 138 tokens to every session and 3,224 once invoked, about $0.0007 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 skills, from other repositories
dev-plan
Transforma um BRIEF (ou ideia já discutida) em PLAN.md atômico — tasks com critério verificável, vertical slices, must-haves observáveis, esforço estimado e pontos de reset de contexto. Sem código no plano. Auto-suficiente para reset — uma nova sessão consegue retomar lendo só o PLAN.md. Use quando o usuário disser…
dev-brainstorm
Grilling estruturado para estressar uma ideia de feature ANTES de planejar. Traduz ideia falada/solta em requisitos, classifica o tamanho (S/M/L), faz uma pergunta por vez sempre com recomendação inline, explora o codebase para resolver dúvidas sem perguntar, captura decisões em BRIEF.md ao vivo e fecha com radar de…
dev-ship
Fechamento de feature — verificação goal-backward antes de declarar pronto. Roda Must-Haves do PLAN.md, executa o demo script, revisa o diff completo procurando bugs e restos (debug logs, TODOs, código morto), passa lente de segurança nos arquivos tocados, escreve SUMMARY.md e arquiva o plano. Use quando o usuário…
infosec-vibecoded-apps
Autonomous security auditor for AI-generated applications. Provide a codebase path and it will automatically detect the stack, execute a comprehensive 12-phase security scan, identify vulnerabilities, and provide a production decision.
collaborating-with-codex
Delegate tasks to Codex CLI for prototyping, debugging, code review, implementation handoff, cross-model second opinions, and multi-turn Codex sessions via SESSIONID.
dev-fix
Loop de diagnóstico disciplinado para bugs — sem PLAN.md, direto ao ponto. Constrói feedback loop reproduzível primeiro, ranqueia hipóteses falsificáveis, instrumenta um probe por hipótese, corrige com teste de regressão e limpa os rastros. Tem modo rápido para bug trivial. Use quando o usuário disser "/dev-fix", "tem…