Memorys: Instructions file for Codex

AGENTS.md

Memorys AGENTS.md is an instructions file for Codex, OpenCode from LeandroPG19/Memorys. It costs 402 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file describing the rules for testing and merging the MemoryIndustry project, including local checks, language-model setup, and test fixtures.

In plain words
What is it for?
Use it to configure supported language-model providers, run local merge gates, check test coverage and mutation results, and keep test databases isolated.
Why use it?
It gives coding agents and contributors a shared contract for deciding whether changes are ready and how tests must be run.

Instructions file for CodexOpenCode

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

This is LeandroPG19/Memorys's own configuration. It tells Codex and OpenCode how to work on Memorys 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 Memorys configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LeandroPG19/Memorys. 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/LeandroPG19/Memorys/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/LeandroPG19/Memorys

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 Memorys AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/leandropg19/memorys/agents-md/github.svg)](https://agentmods.dev/instructions/leandropg19/memorys/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/leandropg19/memorys/agents-md"><img src="https://agentmods.dev/badge/instructions/leandropg19/memorys/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 Memorys AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/leandropg19/memorys/agents-md"><img src="https://agentmods.dev/badge/instructions/leandropg19/memorys/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 402 This file is loaded in full into every session.
When invoked 402 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 $0.00402 $0.00402
Opus 5 $0.00201 $0.00201
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured today against content hash 15350c3314a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Memorys 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 today.

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 · 44 lines

What it actually says

Agent contract — MemoryIndustry

Mergeable (local CI only)

Mergeable means ./scripts/merge-gate.sh (or ./scripts/memory-industry-test.sh all) exited 0 in this turn with a clean log: no SKIPPED, no soft alerts, no “should pass”.

GitHub Actions is not the merge judge.

Generative LLM (easy path)

For humans and agent installers — one command, no hunting env vars:

memory-industry llm list
memory-industry llm set ollama                    # local free
memory-industry llm set deepseek --key sk-...     # or qwen / moonshot / zhipu / …
memory-industry llm status

That writes a small config file and loads it automatically on every start. doctor reports generative_llm.

Also: MCP sampling from the host (Cursor/Claude/Gemini), or any custom MEMORY_INDUSTRY_LLM_BASE_URL.

Encode models (embed / NLI / reranker) stay ONNX via memory-industry models all.

Blind gate extras

  • E2E must cover tools without soft-skip
  • scripts/crap-gate.sh — coverage floor
  • scripts/mutants-gate.sh — kill-rate floor
  • Oracles / fixtures decide green — not an AI opinion

Immutable fixtures

Mutating tests use throwaway DBs (brain_gate / peer). Eval smoke may read the live corpus read-only.

Product ids

  • Display / serverInfo.name: MemoryIndustry
  • Bin / npm / mcpServers key: memory-industry
  • Crate: memory_industry
  • Compat: cuba-memorys binary + legacy CUBA_* env / cache paths for one release
  • MCP tool names cuba_* unchanged this release
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. today First seen · 44 lines · 402 tokens per session scan A 15350c3314a7

Subscribe to this mod's changes

Memorys AGENTS.md is an instructions file published in the GitHub repository LeandroPG19/Memorys (29 stars, last pushed today), licensed Apache-2.0. It adds 402 tokens to every session, about $0.0020 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 2026-09-12.

Related

Other instructions, from other repositories

vibetags com-example-service-NewAnnotationsShowcase-SandboxTestHelper.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for sandboxtesthelper and sandbox restriction.

PIsberg/vibetags · 97 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens