What is c166-ghidra-module AGENTS.md?

Project-specific instructions for changing a Ghidra processor extension for Infineon C166 and C167 chips. Ghidra is a tool for examining compiled programs without their source code.

They are for tracing affected code, consulting the chip manual, reusing existing translation paths, and adding small regression tests.

They reduce the risk of changing how instructions, addresses, or decompiled code are interpreted incorrectly.

How keyhana/c166-ghidra-module configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to keyhana/c166-ghidra-module. 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/keyhana/c166-ghidra-module/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/keyhana/c166-ghidra-module

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/keyhana/c166-ghidra-module/agents-md/github.svg)](https://agentmods.dev/instructions/keyhana/c166-ghidra-module/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/keyhana/c166-ghidra-module/agents-md"><img src="https://agentmods.dev/badge/instructions/keyhana/c166-ghidra-module/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/keyhana/c166-ghidra-module/agents-md"><img src="https://agentmods.dev/badge/instructions/keyhana/c166-ghidra-module/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 900 This file is loaded in full into every session.

When invoked 900 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	$0.00900	$0.00900
Opus 5.5	$0.00360	$0.00360
Sonnet 5.5	$0.00180	$0.00180
Haiku 4.5	$0.00090	$0.00090

Measured 2mo ago against content hash 73ccd239abd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

c166-ghidra-module 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 2mo 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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

C166 Ghidra Module

Ghidra processor extension for Infineon C166/C167 devices. Core risk: translating 16-bit operands into correct 24-bit addresses without changing instruction or decompiler semantics.

Working Rules

Trace every caller and representation affected by a change: SLEIGH semantics, program context, analyzer references, injected p-code, and decompiler output.
Before changing instruction encoding, flags, addressing, or timing windows, read relevant instruction in c166ism.md. Treat manual as architectural source of truth; existing implementation may contain bug being fixed.
Reuse existing SLEIGH subtable, analyzer, injector, or script path before adding another translation layer.
Keep generated files out of source changes. Gradle compiles staged c166.sla for headless tests and removes source-tree copy before extension builds.
Leave smallest runnable regression that fails on original bug and checks externally visible result: disassembly, reference target, p-code, or decompilation.
Always checkout to main and fetch upstream changes and start from a new branch before starting to change code.

Addressing Invariants

DPP:  (DPP[offset >> 14] << 14) | (offset & 0x3FFF)
EXTP: (page << 14)              | (offset & 0x3FFF)
EXTS: (segment << 16)           | (offset & 0xFFFF)

Resolution priority: EXTS, EXTP, DPP, then raw offset when context is unknown.
EXTP uses low 14 offset bits; EXTS uses full 16-bit offset.
EXTP/EXTS apply only for encoded instruction-count window.
Read DPP and extension registers at instruction address context.
Never derive missing DPP value from operand selector; that creates phantom refs.
Listing references do not affect decompiler. Change decompiler behavior through p-code (segment()/injectors) or JumpTable.writeOverride().

Change Routing

Change	Primary location
Instruction encoding, semantics, flags	`data/languages/c166.sinc`
Calling convention or callother mapping	`data/languages/c166.cspec`
Language/compiler registration	`data/languages/c166.ldefs`
SFR symbols or segment operation	`data/languages/*.pspec`
Static address references	`C166AddressAnalyzer.java`, `GetPagedOffset.java`
Register-offset p-code	`RegOffsetAddr.java`
Custom p-code operation	`PcodeInject.java` plus matching injector
Interactive repair workflow	`ghidra_scripts/`
Headless regression	`tests/headless/` and `build.gradle`

Read the full file on GitHub · 83 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.

2mo ago First seen · 83 lines · 900 tokens per session scan A 73ccd239abd9

Subscribe to this mod's changes

c166-ghidra-module AGENTS.md is an instructions file published in the GitHub repository keyhana/c166-ghidra-module (61 stars, last pushed 2d ago), licensed MIT. It adds 900 tokens to every session, about $0.0036 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.

c166-ghidra-module AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
c166-ghidra-module AGENTS.mdkeyhana/c166-ghidra-module	Instructions file	61	2d ago	MIT	A	900	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

c166-ghidra-module: Instructions file for Codex