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 agentmods add agents/pome223/missionos/perception-corroboration-bindinggit clone --depth 1 https://github.com/pome223/missionosWrote 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/agents/pome223/missionos/perception-corroboration-binding)<a href="https://agentmods.dev/agents/pome223/missionos/perception-corroboration-binding"><img src="https://agentmods.dev/badge/agents/pome223/missionos/perception-corroboration-binding.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01148 |
| Opus 5 | $0.00000 | $0.00574 |
| Sonnet 5 | $0.00000 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
perception-corroboration-binding 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 5d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perception Corroboration Binding
This contract binds one live VLM observation to one exact camera frame and one independently observed LaserScan candidate. It is evidence for recovery deliberation. It does not approve, dispatch, execute, verify mission completion, or create physical authority.
LLM judges.
Human approves.
Rules constrain.
Executor acts.
Verifier checks.
Repair loops.
Headless TurtleBot3 sensor profile
Headless execution does not prevent ROS image topics. The stock TurtleBot3
burger model has /scan but no RGB camera. When camera perception is enabled,
the Docker launchers select the stock waffle_pi model by default; it publishes
both /camera/image_raw and /scan under Xvfb. An operator may override the
model explicitly:
export MISSIONOS_TURTLEBOT3_CAMERA_PERCEPTION_ENABLED=1
export MISSIONOS_TURTLEBOT3_SIM_MODEL=waffle_pi
export MISSIONOS_TURTLEBOT3_PERCEPTION_SIDECAR_ADK_ENABLED=1
export MISSIONOS_TURTLEBOT3_PERCEPTION_SIDECAR_MODEL_ID=gemini-3.1-flash-lite
The headless Gazebo smoke also sets ROS2_NAV2_USE_SIM_TIME=1 internally. It
keeps the bridge TF buffer in the /clock domain, so the required
map <- lidar_frame lookup uses the LaserScan timestamp without treating a
simulator timestamp as expired host-wall-clock history. Hardware remains
wall-clock by default.
The usual burger default remains unchanged when camera perception is off.
The focused headless capture smoke starts waffle_pi, adds one collision-backed
red box 0.85 m in front of the robot, and writes a PNG plus bridge receipt:
scripts/smoke_turtlebot3_headless_perception_capture_docker.sh
With Vertex ADC configured, run the live source-bound VLM check immediately after capture:
export GOOGLE_GENAI_USE_VERTEXAI=true
export GOOGLE_CLOUD_PROJECT="$(gcloud config get-value project)"
export GOOGLE_CLOUD_LOCATION=global
export MISSIONOS_LLM_BACKEND=gemini
export MISSIONOS_TURTLEBOT3_PERCEPTION_SIDECAR_ADK_ENABLED=1
export MISSIONOS_TURTLEBOT3_PERCEPTION_SIDECAR_MODEL_ID=gemini-3.1-flash-lite
.venv/bin/python scripts/smoke_turtlebot3_live_perception_binding.py \
--capture-receipt output/turtlebot3_perception_smoke/capture.json \
--image output/turtlebot3_perception_smoke/frame.png
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.
- 5d ago First seen · 132 lines · 0 tokens per session scan A 0552ae8a1e16
perception-corroboration-binding is an agent published in the GitHub repository pome223/missionos (2 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,148 tokens. 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 2026-08-31.
Other agents, from other repositories
homelab-architect
Designs home and small-lab network plans from hardware inventory, goals, and operator experience level, with safe staged changes and rollback guidance.
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
network-config-reviewer
Reviews router and switch configurations for security, correctness, stale references, risky change-window commands, and missing operational guardrails.
network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.
agent_types
This document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.…
server_client_architecture
Device agents in UFO are partitioned into server and client components, separating high-level orchestration from low-level execution. This architecture enables safe, scalable, and flexible task execution across heterogeneous devices through the Agent Interaction Protocol (AIP).