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 agodianel/esp32-claude-workbench --skill esp32_test_plangit clone --depth 1 https://github.com/agodianel/esp32-claude-workbenchWrote 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/agodianel/esp32-claude-workbench/esp32_test_plan)<a href="https://agentmods.dev/skills/agodianel/esp32-claude-workbench/esp32_test_plan"><img src="https://agentmods.dev/badge/skills/agodianel/esp32-claude-workbench/esp32_test_plan/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/agodianel/esp32-claude-workbench/esp32_test_plan"><img src="https://agentmods.dev/badge/skills/agodianel/esp32-claude-workbench/esp32_test_plan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00020 | $0.00703 |
| Opus 5 | $0.00010 | $0.00351 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
esp32_test_plan 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 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.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESP32 Test Plan
Generate a comprehensive test plan covering all applicable testing layers for a firmware change.
When to Use
- After an implementation contract is accepted.
- Before starting implementation.
- When adding test coverage to existing code.
Steps
1. Classify the Change
Determine which testing layers apply:
| Layer | Applies When | Tools |
|---|---|---|
| Repository logic | Change involves Python tooling or templates | pytest |
| Host-side logic | Change involves pure C logic (parsers, state machines, encoders) | pytest + native compilation |
| ESP-IDF unit tests | Change modifies an isolated component | ESP-IDF unity framework |
| Target integration | Change requires real hardware validation | pytest-embedded |
| Static analysis | Always | cppcheck, compiler warnings |
2. Identify Test Cases
For each applicable layer, list specific test cases:
Positive cases: Expected behavior with valid inputs. Negative cases: Behavior with invalid inputs, null pointers, edge values. Boundary cases: Limits of buffers, ranges, timeouts. Concurrency cases: Race conditions, shared state under load. Error cases: Failure paths, recovery behavior.
3. Define Test Infrastructure
Specify what is needed:
- New test files to create.
- Fixtures or mocks required.
- Test data or configuration.
- Hardware requirements (if any).
4. Set Pass/Fail Criteria
For each test case:
- Expected result.
- Acceptable tolerance (for timing or analog tests).
- Required evidence (log output, assertion pass, measurement).
5. Generate Test Plan Document
Use the template at missions/templates/test_plan_template.md:
# Test Plan: [Feature Name]
## Change Reference
- Contract: [link to implementation contract]
- Mission: [link to mission file]
## Test Layers
### Layer 1: Repository Logic
| Test Case | Input | Expected Output | Status |
|-----------|-------|-----------------|--------|
### Layer 2: Host-Side Logic
| Test Case | Input | Expected Output | Status |
|-----------|-------|-----------------|--------|
### Layer 3: ESP-IDF Unit Tests
| Test Case | Component | Expected Behavior | Status |
|-----------|-----------|-------------------|--------|
### Layer 4: Target Integration
| Test Case | Setup Required | Expected Behavior | Status |
|-----------|---------------|-------------------|--------|
## Infrastructure Requirements
- [ ] [Requirement]
## No-Hardware Tests
[List tests that can run without ESP32 hardware]
## Hardware-Required Tests
[List tests that need real hardware, marked with pytest `@pytest.mark.hardware`]
## Coverage Goals
- Statement coverage target: [X%]
- Branch coverage target: [X%]
- Critical paths that MUST be covered: [list]
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.
- 10d ago First seen · 105 lines · 20 tokens per session scan A 525636d2336c
esp32_test_plan is a skill published in the GitHub repository agodianel/esp32-claude-workbench (79 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 703 once invoked, about $0.0001 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
jetson-video-pipeline
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
code-plan
Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
ros2-robotics
Best practices for ROS 2 robotics development, covering package structure, nodes, topics/services/actions, launch files, QoS, tf2 transforms, and testing. Use when creating ROS 2 packages, writing nodes in rclpy or rclcpp, defining custom messages/services/actions, writing launch files, configuring QoS profiles…
SmartHome Video Anomaly Benchmark
VLM evaluation suite for video anomaly detection in smart home camera footage.