What is vexic AGENTS.md?

Repository instructions for coding agents working on Vexic, a local Python memory system for long-running agents. They describe the project structure, supported components, boundaries, and contribution rules.

They guide work in Vexic’s contract models, SQLite-backed service, memory components, tests, and local or hosted MCP adapters.

They give an agent a shared source of truth before it edits, reviews, debugs, or suggests changes. They also clarify which hosted features are outside the project’s current scope.

How PyroDonkey/vexic configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to PyroDonkey/vexic. 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/PyroDonkey/vexic/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/PyroDonkey/vexic

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/pyrodonkey/vexic/agents-md/github.svg)](https://agentmods.dev/instructions/pyrodonkey/vexic/agents-md)

Your own site

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

Per session 5,319 This file is loaded in full into every session.

When invoked 5,319 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	$0.05319	$0.05319
Opus 5.5	$0.02128	$0.02128
Sonnet 5.5	$0.01064	$0.01064
Haiku 4.5	$0.00532	$0.00532

Measured 2mo ago against content hash 8dfb886c7630, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vexic 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 · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vexic Agent Instructions

Contributor and maintainer guidance for automated agents working in this repository. This is engineering workflow documentation, not the product README.

Single source of truth for agents working in this repository. Plain markdown, no tool-specific syntax.

Project

Vexic is the standalone memory system extracted from a private source host: a provenance-first, replayable memory core for long-running agents.

The current v0.1 package is a local Python core with:

public contract models in src/vexic/contract
a local SQLite-backed reference service in src/vexic/service.py
memory storage, retrieval, and Light/REM/Deep primitives under src/vexic
conformance and reliability tests under tests

Managed hosted auth stacks, billing, dashboards, public marketplace MCP, mature remote MCP, and managed operations are out of scope for v0.1. The read-only local stdio MCP MVP is the local adapter slice. The in-process hosted MVP shell in src/vexic/hosted.py may bind Vexic-scoped API keys to tenant/project/capability scope for internal staging, and the hosted FastAPI adapter may expose the narrow read-only native HTTP MCP /mcp slice described in ADR 0010. This is not a public HTTP service or production control plane. The private source host remains the first-party consumer; see docs/provenance.md for extraction provenance.

Architecture Boundaries

These are settled boundaries. Do not reintroduce private host runtime code into Vexic.

Package Boundary

Vexic code lives under src/vexic.
Repo-local host adapter files under adapters/ may import public vexic.* APIs as consumers. They are not Vexic package runtime, and provider-secret or live-model wiring belongs there rather than in src/vexic.
Runtime code must not import legacy engine.* modules.
Private source-host paths may appear in provenance or compatibility docs, not as operational dependencies.
LocalMemoryService is a reference local adapter, not a hosted service.
Host-owned extension tables in an existing SQLite database must be preserved. Vexic schema initialization must not create or take ownership of private-host extension tables such as background_tool_audit.

Read the full file on GitHub · 482 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 · 482 lines · 5,319 tokens per session scan A 8dfb886c7630

Subscribe to this mod's changes

vexic AGENTS.md is an instructions file published in the GitHub repository PyroDonkey/vexic (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 5,319 tokens to every session, about $0.0213 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 2026-08-31.

Memory and context ai ai-agent ai-agents ai-memory ai-memory-system artificial-intelligence

vexic AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vexic AGENTS.mdPyroDonkey/vexic	Instructions file	2	21d ago	Apache-2.0	A	5,319	Codex, OpenCode
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

vexic: Instructions file for Codex