toolnet-memory AGENTS.md

Repository instructions for ToolNet Memory, a project-isolated system that stores and supplies useful context to coding agents. It covers memory filtering, storage providers, startup behavior, and integrations with different agents.

In plain words
What is it for?
Use it when developing or modifying ToolNet Memory, its storage backends, project isolation, memory promotion, or integrations with Codex, OpenCode, Agy, and Claude-compatible agents.
Why use it?
It sets boundaries that reduce credential leaks, raw transcript exposure, cross-project memory mixing, and unnecessary recovery work during startup.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/lbt-ai/toolnet-memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/LBT-AI/toolnet-memory

Made for: Codex, OpenCode.

Per session 482 This file is loaded in full into every session.
When invoked 482 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00482 $0.00482
Opus 5 $0.00241 $0.00241
Sonnet 5 $0.00096 $0.00096
Haiku 4.5 $0.00048 $0.00048

Measured 2d ago against content hash e5325a84a4fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toolnet-memory 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 2d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

AGENTS.md · 92 lines

What it actually says

ToolNet Memory — Repository Instructions

This repository contains the ToolNet Memory CLI and runtime.

Working principles

  • Read the current source before making changes.
  • Keep ToolNet Memory project-agnostic. Never hardcode a specific user's project path.
  • Fast startup context must remain local, small, and bounded.
  • Do not automatically run deep recovery commands during agent startup.
  • Do not inject raw transcripts into normal prompts.
  • Durable memory must be filtered, deduplicated, sanitized, and selectively promoted.
  • Never expose credentials, API keys, tokens, passwords, or .env values.
  • Preserve project isolation through .toolnet/project.json.
  • Storage providers must remain pluggable: R2, generic S3, local, and legacy Hugging Face S3.
  • Changes to agent integrations must respect the native mechanism of each agent.

Agent integration model

  • Agy / Antigravity: native hooks and fast context injection.
  • Codex: MCP and project instructions.
  • OpenCode: native integration/plugin mechanisms.
  • Claude-compatible agents: repository instruction files where supported.

All adapters should use the same ToolNet context and memory core rather than duplicating project logic.

Context policy

Normal startup:

minimal context → project rules → current work → small token budget

Do not automatically run:

toolnet-memory session:agy-recover toolnet-memory session:codex-recover toolnet-memory session:opencode-recover toolnet-memory handoff:latest toolnet-memory brief

Those are manual/deep-recovery operations.

Session memory policy

Keep:

  • project rules,
  • technical decisions,
  • architecture decisions,
  • important files changed,
  • confirmed fixes,
  • blockers,
  • deployment rules,
  • next actions.

Discard or heavily filter:

  • system messages,
  • ephemeral messages,
  • reasoning/tool logs,
  • progress output,
  • npm noise,
  • repeated terminal output,
  • duplicate facts,
  • secrets.

Quality checks

Before committing code changes, run:

npm run lint npm run format:check npm run typecheck npm test npm run build:release

Do not claim completion if these checks fail.

Releases

Never republish an existing npm version.

Before publishing:

npm view toolnet-memory@latest version node -p "require('./package.json').version"

If the version already exists on npm, bump the package version first.

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. 2d ago First seen · 92 lines · 482 tokens per session scan A e5325a84a4fe

Subscribe to this mod's changes

toolnet-memory AGENTS.md is an instructions file published in the GitHub repository LBT-AI/toolnet-memory (4 stars, last pushed 7d ago), licensed MIT. It adds 482 tokens to every session, about $0.0024 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 2026-08-31.

Related

Other instructions, from other repositories

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

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 · 7,104 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 · 5,182 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 · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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