Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeic/vibe-icnpx agentmods add skills/vibeic/vibe-ic/fpga-led-probe-allocationWrote 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/vibeic/vibe-ic/fpga-led-probe-allocation)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/fpga-led-probe-allocation"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/fpga-led-probe-allocation/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/vibeic/vibe-ic/fpga-led-probe-allocation"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/fpga-led-probe-allocation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.02575 |
| Opus 5 | $0.00046 | $0.01288 |
| Sonnet 5 | $0.00018 | $0.00515 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
fpga-led-probe-allocation 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FPGA LED probe allocation
When to use
- The host machine has no oscilloscope / SignalTap on the rig.
- The user has a DE10-Lite, DE10-Nano, or similar board with a row of LEDs as the only on-board observability.
- A USB webcam (or phone) will be used to capture LED states for
before/after diff via
device_camera_capture/device_camera_led_diff(mcp-eda v0.99+).
The four probe modes
Picking the right mode for each signal is the difference between an LED that flashes too fast for a 30 fps webcam to catch and one that holds long enough for diff-capture but doesn't lie about the system state.
| Mode | Visible duration | Use when | Pattern |
|---|---|---|---|
| instantaneous | 1 cycle | signal is steady-state (FSM in IDLE, register holds value) | assign LED[N] = signal; |
| pulse-stretched | ≥ 5 ms | signal is a 1-cycle pulse you want to see | pulse_stretch #(50000) u_st(.clk(clk_50m), .pulse_in(signal), .led_out(LED[N])); |
| sticky | latched until reset / next event | signal is a "did this event ever happen?" flag | always_ff @(posedge clk_50m) if (rst_n & signal) seen_q <= 1; assign LED[N] = seen_q; |
| byte-display | a multi-LED column showing 8 bits of a byte | byte register snapshot | assign LED[7:0] = byte_q; (consumes 8 LEDs) |
How to allocate
For a 10-LED board (DE10-Lite has LEDR[9:0]):
| LED | Mode | Signal | What it tells you |
|---|---|---|---|
| LEDR[9] | sticky | tx_done_q |
"RTL ever finished a TX packet" |
| LEDR[8] | sticky | cmd_decoded_q |
"RTL ever decoded a cmd opcode" |
| LEDR[7:0] | byte-display | last_response_byte |
most recent response byte the device sent |
That layout consumes all 10 LEDs and gives you (a) a "did anything happen?" signal at LEDR[9:8], (b) the exact byte at LEDR[7:0]. For a host-driven test you can sequence:
- Hold reset, capture (everything LOW = baseline).
- Release reset, send cmd 0x70.
- Capture again; LEDR[9:8] tell you the FSM at least executed a TX and decoded a cmd; LEDR[7:0] should show the response byte.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 204 lines · 91 tokens per session scan A 34fc36cfd3c7
fpga-led-probe-allocation is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 2,575 once invoked, about $0.0005 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
analog-netlist-crawl
Crawl and analyze post-layout parasitic netlists without running SPICE. Answers "what's the effective resistance from node A to node B across this massive R mesh?", "inside the VREFN mesh, which device pins are electrically farthest apart?", "which nets have the worst coupling?", "where does settling bottleneck?" — by…
analog-verify
Pre-simulation review and Spectre simulation verification for analog circuits. Reviews circuit netlist and testbench, runs simulation, produces margin report. Use after analog-design completes a netlist.
analog-design
Transistor-level circuit design for one analog sub-block. Produces Spectre netlist with hand-calculation rationale. Use when designing a specific circuit block after architecture is defined.
analog-pipeline
MANDATORY — MUST load this skill when the user mentions: OTA, ADC, PLL, comparator, bandgap, LDO, amplifier, opamp, or any analog/mixed-signal IC design task. Full analog design pipeline: spec -> architecture -> design -> verify -> deliver. Orchestrates analog-decompose, analog-behavioral, analog-design…
analog-audit
Audit analog circuit netlists for correctness, quality, and risks. Supports both pre-layout (schematic) and post-layout (extracted) netlists. Post-layout mode filters massive parasitic netlists before auditing. Works without EDA. TRIGGER on: "audit", "review netlist", "check this circuit", "design review"…
analog-decompose
Architect Phase 1: decompose top-level analog spec into sub-block specs. Use when starting a new analog design to select architecture, allocate budgets, define sub-block specs, write testbenches, and create verification plans.