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/pilan-ai/mnemo/agents-mdgit clone --depth 1 https://github.com/Pilan-AI/mnemoWrote 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/pilan-ai/mnemo/agents-md)<a href="https://agentmods.dev/instructions/pilan-ai/mnemo/agents-md"><img src="https://agentmods.dev/badge/instructions/pilan-ai/mnemo/agents-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 | $0.02470 | $0.02470 |
| Opus 5 | $0.01235 | $0.01235 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
mnemo 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mnemo
Purpose
Memory for AI-assisted development — Indexes AI coding sessions from 12+ tools (Claude Code, OpenCode, Gemini CLI, Cursor, etc.) into a unified, searchable SQLite database with FTS5 full-text search.
Status: Active development, Production-ready Version: 1.3.1
Key Files
| File | Description |
|---|---|
main.go |
Entry point — CLI initialization |
go.mod |
Go module definition (Go 1.23+) |
README.md |
Project overview, install, usage |
CONTRIBUTING.md |
Development setup and contribution guide |
CHANGELOG.md |
Version history and releases |
LICENSE |
MIT License (17588691 CANADA INC.) |
Project Structure
mnemo/
├── main.go
├── cmd/ # CLI commands (cobra)
│ ├── root.go # Root command + configure
│ ├── index.go # Indexing orchestrator + onboarding
│ ├── index_helpers.go # Shared helpers (truncate, inferProvider, etc.)
│ ├── index_claude.go # Claude Code adapter (JSONL)
│ ├── index_opencode.go # OpenCode adapter (JSON)
│ ├── index_gemini.go # Gemini CLI adapter (JSON)
│ ├── index_cursor.go # Cursor adapter (SQLite)
│ ├── index_codex.go # Codex CLI adapter (JSONL)
│ ├── index_amp.go # Amp adapter (JSON + usage ledger)
│ ├── index_crush.go # Crush adapter (SQLite)
│ ├── index_cline.go # Cline/Roo/Kilo Code adapter (JSON)
│ ├── index_kiro.go # Kiro adapter (JSON)
│ ├── index_antigravity.go # Antigravity adapter (JSONL)
│ ├── index_vscode.go # VS Code AI chat adapter (SQLite)
│ ├── search.go # Full-text search command
│ ├── serve.go # MCP server (4 tools: search, context, recent, tools)
│ ├── blocks.go # 5-hour usage block display
│ ├── projects.go # Project management
│ ├── tools.go # Tool detection + path helpers
│ ├── add.go # Custom path indexing
│ ├── install.go # Plugin installer
│ ├── context.go # Context generation
│ ├── recent.go # Recent sessions display
│ ├── status.go # System status display
│ ├── version.go # Version info
│ └── onboarding.go # First-run experience
├── internal/
│ ├── db/ # SQLite database layer
│ │ ├── sqlite.go # Schema, migrations, init, execer interface
│ │ ├── messages.go # Message CRUD (with Tx variants)
│ │ ├── sessions.go # Session CRUD + typed RecentSession queries
│ │ ├── search.go # FTS5 search + BM25 composite ranking
│ │ ├── projects.go # Project discovery + classification
│ │ ├── token_usage.go # Token/cost tracking + typed stats structs
│ │ └── blocks.go # 5-hour session blocks + usage stats
│ └── tui/ # Bubble Tea TUI components
│ ├── styles.go # Catppuccin color palette + shared styles
│ └── projects.go # Interactive project selector
├── proxy/ # HTTP proxy for Claude API context injection
│ └── server.go # Intercepts API calls, injects mnemo context
├── docs/ # Documentation
├── assets/ # Media assets
└── scripts/ # Build and automation scripts
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.
- 4d ago First seen · 225 lines · 2,470 tokens per session scan A d0670887b907
mnemo AGENTS.md is an instructions file published in the GitHub repository Pilan-AI/mnemo (53 stars, last pushed 3mo ago), licensed MIT. It adds 2,470 tokens to every session, about $0.0123 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.
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.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
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.