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 layer1labs/specsmith --skill saleae-mcp-debuggergit clone --depth 1 https://github.com/layer1labs/specsmithWrote 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/layer1labs/specsmith/saleae-mcp-debugger)<a href="https://agentmods.dev/skills/layer1labs/specsmith/saleae-mcp-debugger"><img src="https://agentmods.dev/badge/skills/layer1labs/specsmith/saleae-mcp-debugger.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 | $0.00969 |
| Opus 5 | $0.00000 | $0.00485 |
| Sonnet 5 | $0.00000 | $0.00194 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
saleae-mcp-debugger 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 7d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Saleae Logic 2 MCP Debugger Skill
Use this skill for hardware-in-the-loop firmware capture and decode workflows through the Saleae Logic 2 MCP server.
1) Version compatibility check procedure
- Minimum supported Logic 2 version:
2.4.0+(validated on 2.4.44). - On startup, call
initializeand capture:- MCP server version
- API/protocol version
- If version is missing, unknown, or below 2.4.0, fail fast with remediation:
- Upgrade Logic 2 to 2.4.0 or newer.
- Re-enable Automation/MCP endpoint.
- Re-run initialization before issuing capture/analyzer calls.
2) MCP connection setup (HTTP transport, port 10530)
- Transport endpoint:
http://127.0.0.1:10530. - Ensure Logic 2 Automation settings expose the MCP server on localhost.
- Parse tool results robustly: result payloads are text JSON in
result.content[0].text. - Required parsing behavior:
- Validate JSON before field access.
- Handle missing keys with explicit error messages.
- Preserve raw text payload in logs when parsing fails.
3) Capture lifecycle (start → wait → export → close)
- Discover device:
get_devices. - Begin capture:
start_capture. - Wait until completion or timeout:
wait_capture. - Optional explicit end:
stop_capture(if capture mode requires it). - Export data/artifacts:
export_raw_data_csv,export_raw_data_binary,export_data_table_csv, orlegacy_export_analyzer. - Persist capture if needed:
save_capture. - Release resources:
close_capture.
Core tools to support:
get_devicesstart_capturestop_capturewait_captureload_capturesave_captureclose_captureadd_analyzerremove_analyzeradd_high_level_analyzerremove_high_level_analyzerexport_raw_data_csvexport_raw_data_binaryexport_data_table_csvlegacy_export_analyzer
4) SPI analyzer setup with known edge cases and fallback strategy
- Use MCP field names exactly:
analyzerNameanalyzerLabel
- Known integration edge case:
- Setting
MISOmay return:[INVALID_REQUEST] Invalid value type for analyzer setting "MISO", expected number
- This has been observed for tested encodings and should be treated as a known interoperability issue.
- Setting
- Fallback/retry strategy:
- Retry with numeric channel index values for all SPI channel fields.
- Retry with minimal SPI settings (
Clock,Enable,MISO) and defaults for others. - If still rejected, continue capture export without SPI analyzer and emit a structured warning with remediation.
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.
- 7d ago First seen · 102 lines · 0 tokens per session scan A 94225ae7c8e8
saleae-mcp-debugger is a skill published in the GitHub repository layer1labs/specsmith (7 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 969 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 skills, from other repositories
dependency-scan
Phase 1 mandatory dependency scan. Runs all 6 checks in a single invocation - route hrefs, component import consumers, shared type/utility consumers, test file references, FK references, access control policies. Returns a structured report per check with exact file paths and line numbers. Invoke once with the full…
systematic-debugging
Enforce root-cause investigation before any fix. Use when encountering a bug, test failure, unexpected behavior, or build error.
performance-smell-detection
Detect potential code-level performance smells in Java - streams, collections, boxing, regex, object creation. Provides awareness, not absolutes - always measure before optimizing. For JPA/database performance, use jpa-patterns instead.
analyze-kernel-bottleneck
Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis, occupancy calculations, compute/load ratio per tile, and SASS instruction inspection. Produces a decision matrix for optimization strategy selection (cp.async, warp interleaving, tiling…
rviz2
RViz2 visualization for ROS 2: displays, TF frame debugging, markers, saved config files, and the common 'nothing shows up' fixes (fixed frame, QoS, sim time). Use when: 'rviz', 'rviz2', visualizing ROS topics, TF trees, costmaps, or robot models during development. ROS-native desktop debugging tool; for remote/web…
arch-audit
Audit Claude Code architecture files against Anthropic docs and release notes, and verify internal ecosystem consistency. Run on demand to maintain compliance, catch new features, and keep the context system clean.