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/mex-memory/mex/claude-mdgit clone --depth 1 https://github.com/mex-memory/mexWhat 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 | $0.00382 | $0.00382 |
| Opus 5 | $0.00191 | $0.00191 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
agents 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 yesterday.
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.
What it actually says
[Project Name]
What This Is
Non-Negotiables
Commands
After Every Task
After completing any task: update .mex/ROUTER.md project state and any .mex/ files that are now out of date. If no pattern existed for the task you just completed, create one in .mex/patterns/.
Navigation
At the start of every session, read .mex/ROUTER.md before doing anything else.
For full project context, patterns, and task guidance — everything is there.
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.
- yesterday First seen · 40 lines · 382 tokens per session scan A 2ba41ed19c03
agents is an instructions file published in the GitHub repository mex-memory/mex (1,536 stars, last pushed yesterday), licensed MIT. It adds 382 tokens to every session, about $0.0019 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
Atomic-Spec AGENTS.md
Instructions for Chappygo-OS/Atomic-Spec, covering agents.md — adding a new ai agent to atomic spec, about atomic spec and the atomicspec cli, general practices, adding new agent support and current supported agents.
Atomic-Spec CLAUDE.md
Instructions for Chappygo-OS/Atomic-Spec, covering claude.md, what this repository is, architecture — the phase pipeline, critical conventions and common commands.
mcp-server GEMINI.md
Instructions for contextstream/mcp-server: Persistent project memory for AI coding agents. Connect via hosted MCP.
ccRecall CLAUDE.md
Claude Code instructions for tznthou/ccRecall, covering ccrecall — ai memory service for claude code, 定位, 指令, 技術約束 and 架構.
muse CLAUDE.md
Instructions for myths-labs/muse, covering 🏛 constitution — muse, iron rules, skill-driven execution, context health pre-check and safety protocols.
pluribus copilot-instructions.md
Instructions for caioribeiroclw-pixel/pluribus, covering project, stack, conventions, constraints and goals.