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 commands/mathisk2095/jko-claude-plugins/esp-debuggit clone --depth 1 https://github.com/mathisk2095/jko-claude-pluginsWhat 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 | $0.00011 | $0.00571 |
| Opus 5 | $0.00005 | $0.00285 |
| Sonnet 5 | $0.00002 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
esp-debug 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESP32 Debug Assistant
First: Use the esp32-expert skill. → Consult debugging reference for crash decoding, GDB commands, and the code inspection checklist.
Think like a field support engineer with a crashed device and only a serial log to work with. Find the root cause, not just the symptom.
Process
-
Identify the problem type from $ARGUMENTS:
- Crash log / Guru Meditation: Decode the backtrace and register dump
- Watchdog timeout: Identify which task is blocked and why
- Hang / freeze: Check for deadlocks, infinite loops, blocked tasks
- Peripheral not working: Check wiring, configuration, timing
- Memory issues: Check heap, fragmentation, stack overflow
- WiFi/BLE issues: Check events, reconnection, signal strength
-
For crash logs:
- Identify the exception type (LoadProhibited, StoreProhibited, etc.)
- Decode addresses to file:line using addr2line
- Check for null pointer patterns (0x00000000)
- Check if addresses are in IRAM, DRAM, flash, or peripheral space
- Look at the backtrace to identify the call chain
-
For hangs:
- Suggest enabling task runtime stats (
configGENERATE_RUN_TIME_STATS) - Check for potential deadlock scenarios (multiple mutexes)
- Check for tasks waiting on empty queues or unavailable semaphores
- Check Core 0 vs Core 1 affinity issues
- Suggest enabling task runtime stats (
-
For peripheral issues:
- Verify pin assignments match the target variant
- Check if pins conflict with strapping pins or flash SPI
- Verify voltage levels and pullups
- Suggest bus scanning (I2C) or logic analyzer capture (SPI/UART)
- Search for the device datasheet for timing requirements
-
Provide the root cause and a fix, not just a workaround.
Output Format
## Diagnosis
### Symptom
[What the user reported]
### Root Cause
[Identified cause with evidence]
### Fix
[Concrete code changes or configuration changes]
### Prevention
[How to avoid this class of bug in the future]
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 · 70 lines · 11 tokens per session scan A d7fb6ee84be9
esp-debug is a command published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 11 tokens to every session and 571 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 2026-08-31.
Other commands, from other repositories
status
Show tlive daemon, channel, and Codex companion status.
codex-review
Run OpenAI Codex code review on current changes or a specific branch/commit.
stats
Show statistics for saved conversation files.
close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
prompt
Convert a rough ask into a structured XML-tagged prompt using the factory-prompting vocabulary.
submit
Move the current branch's Linear issue to In Review.