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/architecture-exploreWrote 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/architecture-explore)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/architecture-explore"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/architecture-explore/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/architecture-explore"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/architecture-explore.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 | $0.00068 | $0.00978 |
| Opus 5 | $0.00034 | $0.00489 |
| Sonnet 5 | $0.00014 | $0.00196 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
architecture-explore 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 10d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Explore
The decisions with the biggest PPA impact happen before a line of RTL is written. This skill runs a lightweight design-space exploration against a handful of candidate micro-architectures and reports the Pareto frontier.
When to use
- At the start of a new block design
- When the first PPA predictions miss target
- Before committing to an IP from a vendor
- For re-targeting a block to a new process or frequency
Inputs
- Functional spec (from
/spec-review) - PPA targets: area, frequency, power, throughput, latency
- Process node / library
- Workload characterization (for data-path blocks)
- Candidate knobs: pipeline depth, parallel lanes, memory banking, cache size, bus width
Workflow
-
Define the parameter space — typically 3–5 knobs with 2–4 levels each. This is an AI-judgment step: pick the knobs and levels that matter for THIS block and workload (you know the design; the program does not).
-
Build analytic model + prune — do NOT hand-compute the PPA math or eyeball dominance. Encode each candidate as a knob row with the per-unit coefficients and run the deterministic program. It applies the four formulas (Throughput = parallelism × frequency, Area = Σ(units × unit_area)
- memory × bit_area, Power = activity × C × Vdd² × f, Latency = depth × cycle_time) and returns the Pareto frontier (area-minimise, power-minimise, latency-minimise, throughput-maximise) via a dominance filter:
python3 plugins/vibe-ic/programs/arch_dse_pareto.py knobs.json --json arch/dse.jsonknobs.jsonis a list of candidates, each giving its knob values plus the coefficients the formulas need (unit_area,activity,cap,vdd, …). The program is chip-AGNOSTIC and hard-codes no process numbers — you supply the coefficients. It degrades gracefully (reportsstatus: MISSING/ per-candidatenotes) on partial input rather than crashing or over-flagging. Thepareto_frontierlist in the output is the set of non-dominated points to carry forward. -
Spot-check the frontier candidates with
/ppa-predict -
Plot (or tabulate) the Pareto frontier from
arch/dse.json -
Recommend 1–2 architectures with rationale. This is an AI-judgment step: the program tells you WHICH points are Pareto-optimal; you decide WHICH of those best fits the PPA target priorities, risk, and roadmap.
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.
- 10d ago First seen · 92 lines · 68 tokens per session scan A 9d89029ecc5b
architecture-explore is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 978 once invoked, about $0.0003 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-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-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-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.