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_arch_reviewgit 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_arch_review)<a href="https://agentmods.dev/skills/agodianel/esp32-claude-workbench/esp32_arch_review"><img src="https://agentmods.dev/badge/skills/agodianel/esp32-claude-workbench/esp32_arch_review/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_arch_review"><img src="https://agentmods.dev/badge/skills/agodianel/esp32-claude-workbench/esp32_arch_review.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 | $0.00026 | $0.00852 |
| Opus 5 | $0.00013 | $0.00426 |
| Sonnet 5 | $0.00005 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
esp32_arch_review 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 11d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESP32 Architecture Review
Perform a structured review of firmware architecture focusing on embedded-specific safety and correctness.
When to Use
- Before merging significant changes.
- During implementation contract review.
- When inheriting or auditing an existing project.
- Periodically for long-running projects.
Review Checklist
1. FreeRTOS Safety
- All tasks have explicitly sized stacks (no defaults).
- Stack sizes are appropriate: ≥2048 for simple, ≥4096 for Wi-Fi/BLE tasks.
- No blocking calls in ISRs.
- ISR-safe API variants used where required (
*FromISRfunctions). - Shared resources protected by mutexes.
- No priority inversion risks (or priority inheritance mutexes used).
- Task watchdog timer handled for long-running operations.
- No unbounded loops without
vTaskDelay()ortaskYIELD(). - Critical sections are short (< 1ms).
- Queue/semaphore usage has appropriate timeouts (not
portMAX_DELAYeverywhere).
2. Memory Management
- No large stack-allocated buffers (> 512 bytes).
- Heap allocations checked for NULL.
- DMA buffers allocated with
heap_caps_malloc(MALLOC_CAP_DMA). - Free heap monitored at runtime.
- No memory leaks in error paths (allocated memory freed on failure).
- String buffers have bounds checking.
- No
malloc()inside ISRs.
3. Error Handling
- All
esp_err_treturn values checked. -
ESP_ERROR_CHECK()used only for fatal init errors. - Runtime errors handled gracefully (log + recover or degrade).
- Network operations use retry with backoff.
- Timeout values are defined and reasonable.
- Error paths clean up resources (close handles, free memory).
4. Peripheral Safety
- GPIO pins validated against reserved pin list.
- Peripheral initialization checks for errors.
- De-initialization / cleanup paths exist.
- Bus recovery mechanisms for I2C/SPI.
- ADC2 not used alongside Wi-Fi.
- Pin map is documented and consistent with code.
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.
- 11d ago First seen · 115 lines · 26 tokens per session scan A 82e603b061bc
esp32_arch_review is a skill published in the GitHub repository agodianel/esp32-claude-workbench (79 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 852 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
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
arch-review
Read-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.
cdc-tool-profiles
Internal reference: cdc tool profiles (agent-loaded; do not invoke).
rtl-review
Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.
kicad-pcb-review
KiCad PCB review and manufacturing readiness agent skill for Cursor.
code-review-policy
Internal reference: code review policy (agent-loaded; do not invoke).