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.
npx agentmods add instructions/lbt-ai/toolnet-memory/gemini-mdgit clone --depth 1 https://github.com/LBT-AI/toolnet-memoryWrote 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.
[](https://agentmods.dev/instructions/lbt-ai/toolnet-memory/gemini-md)<a href="https://agentmods.dev/instructions/lbt-ai/toolnet-memory/gemini-md"><img src="https://agentmods.dev/badge/instructions/lbt-ai/toolnet-memory/gemini-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00482 | $0.00482 |
| Opus 5 | $0.00241 | $0.00241 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
toolnet-memory GEMINI.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 3d 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.
This is a copy
100% identical to toolnet-memory AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
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.
- 3d ago First seen · 92 lines · 482 tokens per session scan A e5325a84a4fe
toolnet-memory GEMINI.md is an instructions file published in the GitHub repository LBT-AI/toolnet-memory (4 stars, last pushed 8d 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. It is 100% identical to toolnet-memory AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).