RTLDesignSherpa: Instructions file for Codex

AGENTS.md

RTLDesignSherpa AGENTS.md is an instructions file for Codex, OpenCode from sean-galloway/RTLDesignSherpa. It costs 467 tokens per session, scanned A, original, MIT.

Repository instructions that define a required house style for block and microarchitecture diagrams. They require Graphviz DOT, a text format for diagrams, and specify how data and command flows, shapes, and labels should appear.

In plain words
What is it for?
Use them when creating or reviewing diagrams in the repository's documentation, books, notes, or FPGA materials. They guide layout, arrow direction, scheduler shape, and flow labels.
Why use it?
They prevent inconsistent diagrams across the repository and make important flows easier to follow. The rules also point contributors to the handbook and a reference image.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is sean-galloway/RTLDesignSherpa's own configuration. It tells Codex and OpenCode how to work on RTLDesignSherpa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RTLDesignSherpa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sean-galloway/RTLDesignSherpa. 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/sean-galloway/RTLDesignSherpa/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/sean-galloway/RTLDesignSherpa

Made for: Codex, OpenCode.

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 RTLDesignSherpa AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sean-galloway/rtldesignsherpa/agents-md/github.svg)](https://agentmods.dev/instructions/sean-galloway/rtldesignsherpa/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sean-galloway/rtldesignsherpa/agents-md"><img src="https://agentmods.dev/badge/instructions/sean-galloway/rtldesignsherpa/agents-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.

agentmods 80×15 button for RTLDesignSherpa AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sean-galloway/rtldesignsherpa/agents-md"><img src="https://agentmods.dev/badge/instructions/sean-galloway/rtldesignsherpa/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 467 This file is loaded in full into every session.
When invoked 467 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00467 $0.00467
Opus 5.5 $0.00187 $0.00187
Sonnet 5.5 $0.00093 $0.00093
Haiku 4.5 $0.00047 $0.00047

Measured 15d ago against content hash f53fa46a4132, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

RTLDesignSherpa AGENTS.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 15d 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.

AGENTS.md · 37 lines

What it actually says

RTLDesignSherpa — standing agent instructions

Block diagrams: house style is BINDING (highest priority for all doc/diagram work)

Every block / microarchitecture diagram in this repo — HAS/MAS books, README figures, vault notes, fpga docs, anything — MUST follow the diagram house style, fixed by the owner's reference (the classic DDR-MC course diagram), and is drawn in graphviz dot. The canonical rules live in the handbook:

vault/handbook/authoring/block-diagrams.md

The reference implementation is the family whole-unit diagram (common_has/assets/graphviz/01_whole_unit.png) — mirror it.

Non-negotiables (rationale + recipes in the handbook note):

  • Three flows traceable at a glance: command top-down the center; write data on its own route; read data back UP its own route (the spatial loop). Flows never share an arrow.
  • The scheduler is the flat wide-edge-up trapezium (shape=invtrapezium — plain trapezium renders as an upside-down mux). Every arrow into it carries a transaction-class label (WR / RMW, RD, REF / ZQ, timer window); the command output leaves the narrow edge with a heavier pen (penwidth=1.8).
  • Every arrow labeled with what it carries. Sideband/optional: dashed, short, labeled. Same-rank (horizontal) edge labels use xlabel — plain labels get overdrawn by node fills.
  • One boundary bar per diagram (PHY at unit scale, layer edge at layer scale). No long same-rank edges. Never two parallel edges between one node pair for two classes (one edge, combined label). Never multiple mixed-direction crossings on one node pair — use the point-node scaffold pattern (handbook note).
  • Render, then READ THE RENDERED PNG AT FULL RESOLUTION and trace the three flows before committing. Never commit an unseen diagram; if a flow cannot be traced with a finger, fix the ranks — not the colors.
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. 15d ago First seen · 37 lines · 467 tokens per session scan A f53fa46a4132

Subscribe to this mod's changes

RTLDesignSherpa AGENTS.md is an instructions file published in the GitHub repository sean-galloway/RTLDesignSherpa (25 stars, last pushed 2d ago), licensed MIT. It adds 467 tokens to every session, about $0.0019 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 2026-10-13.

Related

Other instructions, from other repositories