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/daniloc/mnemion/claude-mdgit clone --depth 1 https://github.com/daniloc/mnemionWrote 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/daniloc/mnemion/claude-md)<a href="https://agentmods.dev/instructions/daniloc/mnemion/claude-md"><img src="https://agentmods.dev/badge/instructions/daniloc/mnemion/claude-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 | $0.11333 | $0.11333 |
| Opus 5 | $0.05666 | $0.05666 |
| Sonnet 5 | $0.02267 | $0.02267 |
| Haiku 4.5 | $0.01133 | $0.01133 |
Grade A, and why
mnemion CLAUDE.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 — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Mnemion
Persistent, evolving shared memory between a human and their AI agents. MCP server on Cloudflare Workers.
Source is organized into component directories, each with a co-located
*.spec.md (intent + ## works when claims + protected ## why). The
coherence harness derives a multi-resolution graph from the spec tree + code,
verifies the specs haven't rotted, and writes the component map + invariant
table into the fenced block below (coherence claude regenerates it; the
freshness gate fails CI if it drifts). entities/ are the two Durable Objects
- their domain logic;
shared/are cross-cutting primitives;src/keeps the worker entry, the MCP render fragment, system docs, and tests. The web app proper is React (underweb/); per-file roles live in each file's top-of-file docblock so the generated block stays the single source of truth.
Per-doc roots: project-docs/archived/ (design docs), mnemion-js/ (the
worker), Mnemion.spec.md (root spec), coherence.config.json (harness
config), scripts/setup.sh (first-run setup).
Future peer: iOS app (Swift).
Derived from 8 components · 68 files · 465 symbols · 16 boundary claims.
Component map (derived)
Each component directory, its spec intent (one line), and its files. Per-file roles are authored elsewhere — the graph only knows component-level intent.
Mnemion /
Cloudflare Worker entry: an OAuth-wrapped MCP server whose one declarative route table is the whole HTTP surface.
files: index.ts, vite.fragment.ts, vite.preview.ts, vite.web.ts, store.ts
Hive entities/Hive
The single per-user Durable Object that owns all SQLite data and funnels every agent write through one kernel-enforced chokepoint.
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 · 524 lines · 11,333 tokens per session scan A fabd5c462e00
mnemion CLAUDE.md is an instructions file published in the GitHub repository daniloc/mnemion (22 stars, last pushed 14d ago), licensed MIT. It adds 11,333 tokens to every session, about $0.0567 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
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).
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.
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.
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.
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).
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.