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/gonzalonicolasr/cortexmem/claude-mdgit clone --depth 1 https://github.com/gonzalonicolasr/cortexmemWrote 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/gonzalonicolasr/cortexmem/claude-md)<a href="https://agentmods.dev/instructions/gonzalonicolasr/cortexmem/claude-md"><img src="https://agentmods.dev/badge/instructions/gonzalonicolasr/cortexmem/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 | $0.00372 | $0.00372 |
| Opus 5 | $0.00186 | $0.00186 |
| Sonnet 5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
cortexmem 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.
What it actually says
Memoria - Persistent Memory System
Memory Protocol
You have access to the Memoria MCP server. Use it AUTOMATICALLY - do not wait for the user to ask.
When to Save (AUTOMATIC - do this without being asked)
Call memoria_save immediately after:
- Bug fixes: What broke, why, how you fixed it
- Architecture decisions: Why you chose approach A over B
- Non-obvious discoveries: Unexpected behavior, gotchas, edge cases
- Configuration changes: Environment, deployment, infra changes
- Patterns established: Conventions, naming, file structure decisions
- User preferences: How the user likes things done
Structured Format
Always use this format:
- title: Short, searchable (verb + object)
- what: Action taken - what was done
- why: Motivation - bug, request, performance
- where_at: Affected files/paths
- learned: Gotchas, edge cases, surprises
- topic_key: Stable ID for evolving topics (e.g. "architecture/auth"). Same key = update instead of duplicate
Session Lifecycle
- Start: Call
memoria_session_startwith goal when beginning work - During: Call
memoria_savefor significant events (automatically) - End: Call
memoria_session_endwith structured summary
Context Loading
Call memoria_context at session start to load relevant memories from previous sessions.
Call memoria_search before starting new work to find related context.
Privacy
Never include secrets, tokens, passwords, or API keys in memories. The system strips common patterns automatically, but be mindful.
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 · 41 lines · 372 tokens per session scan A ea0e093df727
cortexmem CLAUDE.md is an instructions file published in the GitHub repository gonzalonicolasr/cortexmem (1 stars, last pushed 5d ago), licensed MIT. It adds 372 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 2026-08-31.
Other instructions, from other repositories
loomem CLAUDE.md
Instructions for vvooki-sys/loomem, covering claude.md — rules for ai code generators in the loomem repo, router — read the subset that applies, five hard rules (never break these), build & run and repo map (where things live).
trailmem AGENTS.md
AGENTS.md instructions for amitnexTech/trailmem, covering trailmem — agent guide, session boot sequence — do this first, tool usage rules — pick the right tool for the question, graphify — code knowledge graph and trailmem — persistent memory.
exocortex CLAUDE.md
Claude Code instructions for shawnhack/exocortex, covering exocortex, stack, key commands, mcp setup and data directory.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.