assess-synthesis-and-inference

assess-synthesis-and-inference is a skill for Claude Code, Codex from simra-tech/OpenADA. It costs 82 tokens per session (2,421 once invoked), scanned A, original, MIT.

A review workflow for turning RTL, or hardware design code, into a checked netlist mapped to a target chip library. It separates lint, synthesis, and timing results so each claim stays specific.

In plain words
What is it for?
Use it to review synthesis results, investigate unexpected registers, latches, memories, arithmetic, or multiplexers, and compare controlled synthesis experiments.
Why use it?
It helps identify missing or unexpected hardware structures without treating synthesis as proof of simulation behavior, timing, power, or silicon correctness.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the openada plugin — 11 skills shipped together

Good fit Use it to review synthesis results, investigate unexpected registers, latches, memories, arithmetic, or multiplexers, and compare controlled synthesis experiments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/simra-tech/openada/assess-synthesis-and-inference
Install

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.

Any agent
npx skills add simra-tech/OpenADA --skill assess-synthesis-and-inference
Clone the repo
git clone --depth 1 https://github.com/simra-tech/OpenADA

Made for: Claude Code, Codex.

Or install openada, the plugin that ships this one along with the rest of its 11 skills.

Wrote 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.

agentmods badge for assess-synthesis-and-inference

README.md
[![agentmods](https://agentmods.dev/badge/skills/simra-tech/openada/assess-synthesis-and-inference/github.svg)](https://agentmods.dev/skills/simra-tech/openada/assess-synthesis-and-inference)
Your own site
<a href="https://agentmods.dev/skills/simra-tech/openada/assess-synthesis-and-inference"><img src="https://agentmods.dev/badge/skills/simra-tech/openada/assess-synthesis-and-inference/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.

agentmods 80×15 button for assess-synthesis-and-inference

Your own site · 80×15
<a href="https://agentmods.dev/skills/simra-tech/openada/assess-synthesis-and-inference"><img src="https://agentmods.dev/badge/skills/simra-tech/openada/assess-synthesis-and-inference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,421 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.02421
Opus 5 $0.00041 $0.01210
Sonnet 5 $0.00016 $0.00484
Haiku 4.5 $0.00008 $0.00242

Measured 9d ago against content hash d37bdb88728e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

assess-synthesis-and-inference 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 9d 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.

skills/assess-synthesis-and-inference/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Assess Synthesis and Inference

Turn one frozen RTL configuration into reviewable mapped-netlist evidence. Use $openada:openada for semantic operations and normalized results. Keep native invocation mechanics below the contract and keep the RTL, Liberty, technology maps, constraints, and retained netlist authoritative.

Separate the claims

Use these exact layers:

  • Review strict lint through openada.operation/rtl.lint/v1alpha1 and openada.assertion/rtl.lint.clean/v1alpha1 when cleanliness is required.
  • Produce mapping evidence through openada.operation/logic.synthesize/v1alpha1 and openada.assertion/synthesized-netlist.valid/v1alpha1.
  • Treat timing as a later, separate openada.operation/timing.analyze/v1alpha1 result.

A synthesis pass establishes a fresh, structurally validated, fully Liberty-mapped netlist under the recorded policy. It does not establish RTL-to- netlist equivalence, simulation behavior, CDC/RDC safety, DFT readiness, clock-tree feasibility, routed timing, power, area-target satisfaction, or silicon correctness. Keep each absent primitive not evaluated.

Freeze a reproducible synthesis manifest

Record:

  • repository revision, ordered RTL sources, conservatively captured include dependencies, unresolved-literal-include disclosure, and hashes;
  • top, frontend, declared language dialect/revision, include directories, defines, generated sources, and black-box assumptions;
  • exact Liberty and technology-map identities and hashes, selected PVT corner, cell exclusions, and library units;
  • mapping policy, flattening policy, undefined-value policy, delay target and native constraint file when supplied;
  • upstream lint/structural envelope paths, artifact hashes, and statuses;
  • selected operation/feature, implementation and native product/version, evidence directory, result-envelope path, and expected output roles.

Do not substitute a convenient Liberty, corner, macro model, technology map, or top. The current result envelope has no general request or result correlation field, and the v1alpha1 synthesis surface has no module-parameter override. Do not invent an identifier or silently use default parameters when the intended configuration requires an override. Do not compare runs with different ordered sources, captured dependencies, defines, or policies as if they were the same experiment. If a required file or design-intent choice is ambiguous, ask one focused question and stop.

Read the full file on GitHub · 227 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 9d ago First seen · 227 lines · 82 tokens per session scan A d37bdb88728e

Subscribe to this mod's changes

assess-synthesis-and-inference is a skill published in the GitHub repository simra-tech/OpenADA (26 stars, last pushed 27d ago), licensed MIT. It adds 82 tokens to every session and 2,421 once invoked, about $0.0004 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.