agentmods.dev

toon-memory AGENTS.md

toon-memory AGENTS.md is an instructions file for Codex, OpenCode from LuiggiVal08/toon-memory. It costs 666 tokens per session, scanned A, original, MIT.

Project instructions for toon-memory, a tool that stores and recalls information for an agent. They describe its build checks and how its command-line interface, server, encrypted secrets, evidence tracking, and knowledge graph fit together.

In plain words
What is it for?
Use them when developing, reviewing, or verifying toon-memory, especially when working on its command-line tools, server tools, memory quality, secrets, or graph features.
Why use it?
They give contributors a shared reference for changing the project and checking that it still builds, passes tests, and type-checks.

Instructions file for CodexOpenCode

not rated 11 29d ago A scan 666 tokens original MIT
View the source file LuiggiVal08/toon-memory
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/luiggival08/toon-memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/LuiggiVal08/toon-memory

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 toon-memory AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/luiggival08/toon-memory/agents-md.svg)](https://agentmods.dev/instructions/luiggival08/toon-memory/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/luiggival08/toon-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/luiggival08/toon-memory/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 666 This file is loaded in full into every session.
When invoked 666 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 $0.00666 $0.00666
Opus 5 $0.00333 $0.00333
Sonnet 5 $0.00133 $0.00133
Haiku 4.5 $0.00067 $0.00067

Measured 3d ago against content hash 9fbc70cbc7a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toon-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 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.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Build & Verify

npm run build   # esbuild: bin → mcp → cli (sequential)
npm test        # vitest run
npx tsc --noEmit  # type check (CI runs this, no npm script)

Build must complete before tests — tests/cli.test.ts executes bin/toon-memory.js.

Architecture

  • src/bin/toon-memory.ts — Entry point. Routes mcp arg to MCP server, everything else to CLI.
  • src/mcp/server.ts — MCP server (38 tools + 4 resources + 1 prompt).
  • src/mcp/tools.ts — Tool implementations. Each tool is registered with the MCP server.
  • src/mcp/vault.ts — Encrypted secrets sidecar (secrets.toon, AES-256-GCM): store/get/list/forget.
  • src/lib/evidence.ts — Write-path evidence: contradiction detection + evidence levels (verified/unverified/conflict) with recall boosts.
  • src/mcp/consolidation.ts — Cleanup ops plus mergeMemoryFiles (global import merge).
  • src/mcp/scoring.ts — Entry scoring and access tracking (bumpAccessed).
  • src/lib/quality.ts — Quality scoring with staleness decay, merge-dedup, smart recall.
  • src/lib/graph.ts — Knowledge graph: adjacency, BM25, centrality, graph recall.
  • src/cli/setup.ts — CLI commands: init, status, stats, export, import, watch, upgrade, uninstall. Also installs hooks per agent.
  • src/cli/opencode-plugin.ts — OpenCode plugin with intelligent auto-loading (recall by file path on tool.execute.after).

Build outputs (bin/, mcp/, dist/) are gitignored. tsconfig.json type-checks src/ (excluding tests).

Smarter Memory Pattern

When working on files, use memory_recall with the file path to get relevant context:

memory_recall(query: "src/cli/config-writer.ts")  → relevant entries about that file

Instead of dumping ALL memory at session start (wastes tokens), recall only what's relevant to the current task.

Visual Memory Pattern

When the user asks to see the memory graph, or at session start to get a visual overview, call memory_visualize:

memory_visualize(query: "")  → renders interactive graph inline in VS Code Copilot
memory_visualize(query: "auth")  → opens graph with search pre-filled

This renders a D3.js force-directed graph inline in any MCP Apps-compatible host. No server needed.

Read the full file on GitHub · 58 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.

  1. 3d ago First seen · 58 lines · 666 tokens per session scan A 9fbc70cbc7a7

Subscribe to this mod's changes

toon-memory AGENTS.md is an instructions file published in the GitHub repository LuiggiVal08/toon-memory (11 stars, last pushed 29d ago), licensed MIT. It adds 666 tokens to every session, about $0.0033 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 2026-08-30.

Memory and contextclaude-codecursordeveloper-toolsmcp-servermodel-context-protocolopencode
Related

Other instructions, from other repositories

mcp-air AGENTS.md

AGENTS.md instructions for VericyIO/mcp-air, covering agents.md, verification commands, node version, publishing and constants sync.

VericyIO/mcp-air · 286 tokens

Plonk AGENTS.md

Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.

ostapondo/Plonk · 3,557 tokens

minecraft-dev-mcp AGENTS.md

Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).

MCDxAI/minecraft-dev-mcp · 1,145 tokens

vrchat-mcp AGENTS.md

Instructions for BASIC-BIT/vrchat-mcp, covering agents, tool ergonomics goals (distilled), curated output philosophy, specific notes (current direction) and caching considerations (planned).

BASIC-BIT/vrchat-mcp · 1,604 tokens

datadog-mcp CLAUDE.md

Instructions for dreamiurg/datadog-mcp, covering agent instructions, project, stack, commands and releases.

dreamiurg/datadog-mcp · 522 tokens

pubmed-mcp-server CLAUDE.md

Instructions for cyanheads/pubmed-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool.

cyanheads/pubmed-mcp-server · 6,291 tokens