What is naja-scope CLAUDE.md?

A repository instruction file for naja-scope that requires code to use najaeda's low-level Python bindings when working with hardware netlists.

Use it when developing naja-scope or writing exploratory scripts that load or inspect Verilog and SystemVerilog designs.

It prevents experiments from using a higher-level wrapper whose behaviour or names may differ from the raw API used by the project.

How najaeda/naja-scope configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to najaeda/naja-scope. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/najaeda/naja-scope/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/najaeda/naja-scope

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/najaeda/naja-scope/claude-md/github.svg)](https://agentmods.dev/instructions/najaeda/naja-scope/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/najaeda/naja-scope/claude-md"><img src="https://agentmods.dev/badge/instructions/najaeda/naja-scope/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/najaeda/naja-scope/claude-md"><img src="https://agentmods.dev/badge/instructions/najaeda/naja-scope/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 802 This file is loaded in full into every session.

When invoked 802 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00802	$0.00802
Opus 5.5	$0.00321	$0.00321
Sonnet 5.5	$0.00160	$0.00160
Haiku 4.5	$0.00080	$0.00080

Measured 1mo ago against content hash 20851f830820, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

naja-scope CLAUDE.md 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 1mo 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.

CLAUDE.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

naja-scope

Always use the low-level naja Python API, never najaeda's high-level API

When writing code that talks to najaeda — inside src/naja_scope/ or in throwaway exploration scripts — always go through from najaeda import naja (the raw naja.so binding: NLUniverse, NLDB, SNL* objects) and never through najaeda.netlist (the high-level load_verilog/load_system_verilog/ Instance/Term wrapper).

Why: src/naja_scope/loader.py is deliberately built this way already — see its module docstring: "driven directly through the raw naja DB/universe API ... rather than the high-level najaeda.netlist loaders. This keeps naja-scope on the raw layer end to end." The high-level API is a convenience wrapper that can lag, rename, or diverge from the raw layer (e.g. the allow_unknown_designs -> blackbox_unknown_modules rename in najaeda 0.7.11 broke the raw NLDB.loadVerilog binding's kwarg, independent of whatever the najaeda.netlist wrapper did to stay compatible). Exploring or prototyping against the high-level API produces findings that don't reflect what naja-scope itself does at runtime.

How to apply: For any one-off inspection (checking pin roles, instance types, hierarchy, etc.), use naja.NLUniverse / naja.NLDB / naja.SNL* objects directly, the same way loader.py, session.py, and api.py do. Do not import or call najaeda.netlist.* even for quick throwaway scripts.

Regularly recheck the latest CVA6 revision

When upgrading najaeda, preparing a naja-scope release, or maintaining the CVA6 regressions, check the latest upstream CVA6 release and default-branch revision to see whether the pinned baseline can be updated. Do not leave CVA6 pinned indefinitely without retrying newer revisions.

As of 2026-09-26, the verified local regression baseline is CVA6 v5.3.0 (2ef1c1b1fca419354920c5487293bc605294904e), configuration cv32a6_imac_sv32, with najaeda 0.7.25. All three tests in tests/test_zzz_cone_cva6.py and tests/test_zzz_hierarchy_cva6.py pass against its rebuilt snapshot. The demo also pins v5.3.0 in examples/_cva6_fetch.sh.

Read the full file on GitHub · 55 lines

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.

1mo ago Changed · +28 lines · +405 tokens per session 20851f830820
2mo ago First seen · 27 lines · 397 tokens per session scan A 47226467d5bc

Subscribe to this mod's changes

naja-scope CLAUDE.md is an instructions file published in the GitHub repository najaeda/naja-scope (16 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 802 tokens to every session, about $0.0032 per session on Opus 5.5. 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.

Hardware and IoT Languages Python ai-agents eda mcp mcp-server netlist systemverilog

naja-scope CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
naja-scope CLAUDE.mdnajaeda/naja-scope	Instructions file	16	1mo ago	Apache-2.0	A	802	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

naja-scope: Instructions file for Claude Code