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/layer-contract-doctrineWrote 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/layer-contract-doctrine)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/layer-contract-doctrine"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/layer-contract-doctrine/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/layer-contract-doctrine"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/layer-contract-doctrine.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 | $0.00143 | $0.06209 |
| Opus 5 | $0.00072 | $0.03104 |
| Sonnet 5 | $0.00029 | $0.01242 |
| Haiku 4.5 | $0.00014 | $0.00621 |
Grade A, and why
layer-contract-doctrine 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layer Contract Doctrine
Purpose. The L1-L27 corpus is a layered intermediate representation: natural language in, structured JSON through, RTL and back end out. Every gate we own checks a layer against a contract. Nothing in the tree states what the contract IS, so each author re-derives it, and each re-derivation is one more chance to put a fact in a layer that nothing downstream reads.
This skill is that statement. It is deliberately short on things a program can check and long on the three judgements a program cannot make.
Chip-AGNOSTIC: every rule below is a property of the layering, not of any design, PDK, vendor or part number. The measured evidence names L-doc fields, program files and line numbers — never a customer part.
Provenance — which parts are ours and which are borrowed. Stated up front because the difference changes how much weight a section carries.
| Section | Origin |
|---|---|
| §1 (Y-chart refinement, ESL/golden-model, MDA/MDE traceability, ABD) | External. Restated from an external survey of spec→RTL methodology, the same survey cited in the Provenance block of issue #377. Framing borrowed; not independently re-derived here. |
| §2 (the consuming-layer rule + 5 measurements) | Ours. Every measurement is from our own runs and our own tree; each cites the file, line or verdict it rests on. |
| §3 (structural/behavioural boundary; the IP-XACT / SystemRDL / PSS scope table) | External for the standards table, ours for the ladder test that is drawn from it. The scope claims are the standards' own stated exclusions, taken from that survey and not independently verified against the ratified documents. |
| §4 (declarative-layer alignment rule) | External for the recommendation, ours for the coverage measurement (grep result below, re-measured on this tree). |
| §5, §6, §7 | Ours. §7 is from an adversarial re-measurement of our own first attempt at §2.2; the transcript in it was produced on a fixture built for that purpose. |
Treat an external row as direction, not as evidence. Where a section makes a claim about our tree, that claim is measured and cited.
What ships with it
3 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 · 477 lines · 143 tokens per session scan A 4a0dfc7f485c
layer-contract-doctrine is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 143 tokens to every session and 6,209 once invoked, about $0.0007 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.