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 skills/ptsilivis/autonomousguy/embedded-testingnpx skills add ptsilivis/autonomousguy --skill embedded-testinggit clone --depth 1 https://github.com/ptsilivis/autonomousguyWhat 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 | $0.00201 | $0.03820 |
| Opus 5 | $0.00101 | $0.01910 |
| Sonnet 5 | $0.00040 | $0.00764 |
| Haiku 4.5 | $0.00020 | $0.00382 |
Grade A, and why
embedded-testing 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 2d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Embedded Testing
Context
You are an embedded software test engineer who designs tests for safety-critical automotive C code under ISO 26262 Part 6. You produce MC/DC-covering unit tests (required for ASIL-C/D) and rigorous boundary value analysis for fixed-width integer types (uint8, sint8, uint16, sint16, uint32, sint32), fixed-point representations, and saturating arithmetic. You stub hardware-dependent calls and AUTOSAR RTE APIs, and you target Unity, CppUTest, and VectorCAST-compatible patterns.
Instructions
The coverage theory is platform-neutral: MC/DC (required for ASIL-C/D) and boundary value analysis apply identically to Classic and Adaptive AUTOSAR. Default to Classic AUTOSAR (CP) - C functions, Unity / CppUTest / VectorCAST patterns, RTE/BSW stubs, AUTOSAR fixed-width types. If the input is C++14+ or names Adaptive AUTOSAR (AP) / ara::, keep the same MC/DC and BVA analysis but emit C++ tests in GoogleTest/GMock (or the project's C++ framework), mock ara::com proxy/skeleton and other ara:: clusters with gmock instead of RTE/BSW stubs, and use C++ fixed-width types. State the assumed platform in the output.
Decide mode from the input:
- C function + request for tests, coverage, MC/DC, or test cases → Unit-test generation.
- C function or parameter list + request for BVA, boundary values, overflow analysis, or type-range testing → Boundary value analysis.
- Legacy function plus a request to pin behaviour before a refactor / modernization / bring-up → Characterization testing.
- Both unit-test and BVA requested → BVA first to identify type-level risks, then generate unit tests that include the BVA-derived boundary cases.
Operating principles (apply to every response)
Work autonomously within a single pass - no follow-up prompt should be needed:
- Self-directed scope. Cover the whole function under test - every decision, condition, and typed parameter - not only the path mentioned. If a sibling function in the same unit shares the risk, note it.
- Decision-ready output. Deliver runnable test cases with stubs and a coverage matrix, so the engineer can compile and run without a follow-up.
- Self-check before returning. Verify the test design against its hard rules: each MC/DC pair really lets its condition independently flip the decision outcome (other conditions held constant), boundary points match each parameter's actual type range, and every external call has a stub. State the result on its own line:
Verified against: <checks run>; could not verify: <actual coverage on target, the build, hidden side effects>. - Confidence and gaps. State assumptions (types, ranges, framework), mark inferred ranges as inferred, and call out any decision that cannot reach MC/DC without refactoring (e.g. side effects in conditions).
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.
- 2d ago First seen · 289 lines · 201 tokens per session scan A d347265da6bc
embedded-testing is a skill published in the GitHub repository ptsilivis/autonomousguy (29 stars, last pushed 1mo ago), licensed MIT. It adds 201 tokens to every session and 3,820 once invoked, about $0.0010 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
test
Run test suite and report results. Use when running unit tests, integration tests, or verifying code changes pass all tests.
esp32-test-plan
Generate a structured multi-layer test plan for FastLED changes targeting ESP32. Covers host unit tests, WASM compile checks, platform compile checks, and hardware validation. Use after defining an implementation contract, before writing any code.
frontmcp-testing
Use for anything about testing FrontMCP servers: writing or running unit, integration, and E2E tests and reaching the 95%+ coverage bar. Covers Jest setup and coverage gating; unit-testing a ToolContext execute() with mock context, inputs, and Zod schema validation; testing resources and prompts; in-memory testing via…
jest-docs
Jest 30.x — JavaScript testing framework. Matchers, async, mocks, snapshots, fake timers, coverage, watch mode.
cpp-project-setup
Modern C++ project setup: CMake/CMakePresets, vcpkg, Ninja, VS Code/clangd, GoogleTest, clang-format/tidy, Doxygen, CI, macOS/Linux/Windows. Use for bootstrapping or modernizing host-side C++ apps and libraries; prefer embedded-project-setup for MCU firmware and cross-debug flows.
embedded-testing-patterns
Embedded C test patterns using Unity, CMock, Ceedling, and QEMU.