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/scope-pattern-attestationWrote 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/scope-pattern-attestation)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/scope-pattern-attestation"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/scope-pattern-attestation/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/scope-pattern-attestation"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/scope-pattern-attestation.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 | $0.00109 | $0.02089 |
| Opus 5 | $0.00055 | $0.01045 |
| Sonnet 5 | $0.00022 | $0.00418 |
| Haiku 4.5 | $0.00011 | $0.00209 |
Grade A, and why
scope-pattern-attestation 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 6d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scope-pattern-attestation — Layer-3 hardware attestation
Doctrine (v0.1.50): 把修法寫進工具，而非寫進 prompt. Programs run the pattern-match; AI is the backstop on waveform interpretation.
Mandatory Deterministic Preflight
# 1. Capture the scope trace via MCP-EDA:
device_scope_capture({ channel: 1, duration_ms: 100 })
# 2. Then run the pattern-specific check:
python3 plugins/vibe-ic/programs/scope_periodic_pulse_check.py \
--trace <trace.csv> --strict # forbidden-pattern absence
python3 plugins/vibe-ic/programs/scope_reply_preamble_check.py \
--trace <trace.csv> --strict # required-pattern presence
python3 plugins/vibe-ic/programs/scope_response_byte_decode_check.py \
--trace <trace.csv>
python3 plugins/vibe-ic/programs/scope_long_decode.py \
--trace <trace.csv> # long-frame decode
The MCP captures the trace; the 4 programs decide pattern PASS / FAIL deterministically. Refuse to attest a pattern by visual inspection of the scope screenshot when the program can decide it.
This skill closes the third layer of the v0.65 three-layer defense. Sim PASS and static-RTL PASS together are still not proof; the only proof that an IC exhibits (or does not exhibit) a behavioral pattern in silicon is to put a probe on the line and capture it.
Why This Exists
A real bug, caught in v0.64, motivates this skill. The static analyser
timer_freeze_after_state_check.py flagged a wake-timer freeze defect
in wake_ctrl.v: after the bus had entered the awake state, a periodic
timer kept firing pulses on the IO line. A Keysight DSO-X 3014T probe
captured the offending IO line and saw 10 LOW pulses in a 50 ms window
— each ~26 µs wide, gaps 5.000-5.001 ms apart — exactly the buggy
waveform predicted from the static finding.
The static checker (v0.64) and the runtime scope checker (this v0.65 skill) are complementary layers, not duplicates:
| Layer | Catches | Misses |
|---|---|---|
| 1. Sim (testbench) | Logic bugs that the testbench stimulates | Anything not stimulated |
| 2. Static (timer_freeze_after_state_check, etc.) | RTL anti-patterns | Synthesis / mapping artefacts; analog issues |
| 3. scope-pattern-attestation (this skill) | Real silicon behavior | Anything you forgot to probe |
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.
- 6d ago First seen · 199 lines · 109 tokens per session scan A d821053b41b2
scope-pattern-attestation is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 109 tokens to every session and 2,089 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 2026-09-03.
Other skills, from other repositories
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.
boardrepo
Read and review real PCB projects on BoardRepo. Search published hardware designs, open a board's schematic connectivity, bill of materials and files, run KiCad's DRC and ERC, and check a design against a fabrication house's limits. Use whenever the user names a BoardRepo board or URL, asks to find a published board…
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-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"…