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 skills/daxaur/openpaw/c-memorynpx skills add daxaur/openpaw --skill c-memorygit clone --depth 1 https://github.com/daxaur/openpawWrote 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/skills/daxaur/openpaw/c-memory)<a href="https://agentmods.dev/skills/daxaur/openpaw/c-memory"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-memory.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 | $0.00017 | $0.00954 |
| Opus 5 | $0.00009 | $0.00477 |
| Sonnet 5 | $0.00003 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade C, and why
c-memory scanned grade C with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/memory/MEMORY.md Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
If `c-obsidian` is also installed (check `ls ~/.claude/skills/c-obsidian/`), automatically sync memory to Obsidian: How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory — Persistent Context
Store and recall facts, preferences, and context across Claude Code sessions.
How It Works
Memory lives in ~/.claude/memory/ as plain markdown files. Read them at session start, write to them when you learn something important.
Directory Structure
~/.claude/memory/
├── MEMORY.md # Key facts — always read this first
├── people.md # People the user mentions (names, roles, preferences)
├── preferences.md # User preferences (tools, workflows, habits)
├── projects.md # Active projects and their context
└── journal.md # Session log — append-only, dated entries
Session Start
At the beginning of every session, read ~/.claude/memory/MEMORY.md to load context. This file should be concise — under 100 lines.
When to Save
Save to memory when the user:
- Shares their name, role, or preferences
- Mentions people they work with
- Describes a project or recurring task
- Says "remember this" or "don't forget"
- Corrects you about something
Writing Rules
- MEMORY.md: Key facts only. Keep under 100 lines. Update, don't append.
- people.md: Name, role, relationship, preferences. One section per person.
- preferences.md: Tools, workflows, communication preferences.
- projects.md: Project name, status, key files, context.
- journal.md: Append a dated entry at the end of each session summarizing what was done.
Commands
# Read memory
cat ~/.claude/memory/MEMORY.md
# List memory files
ls ~/.claude/memory/
# Append to journal
echo "## $(date +%Y-%m-%d)" >> ~/.claude/memory/journal.md
Example MEMORY.md
# Memory
## User
- Name: Alex
- Role: Frontend developer
- Prefers TypeScript, uses Neovim
- Timezone: PST
## Active Projects
- ctrl.build — DeFi workflow automation (Next.js + Solidity)
- openpaw — CLI tool for Claude Code setup
## Preferences
- Concise responses, no emoji unless asked
- Always use bun instead of npm
- Dark mode everything
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 · 119 lines · 17 tokens per session scan C a3e6dd965308
c-memory is a skill published in the GitHub repository daxaur/openpaw (167 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 954 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
memory-bank
Token-efficient persistent memory system for Claude Code that saves 67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode.…
memory-patterns
Use this skill when managing agent context and memory. Covers short-term vs long-term memory, context compaction, and persistent note-taking patterns.
memory-os
Persistent memory system for AI agents — daily logs, long-term memory, identity files, and heartbeat-driven recall. Solves context amnesia across sessions.
kb-memory
Use when knowledge base and memory system for AI agents. Covers company KB, persistent memory, session recall, and brain architecture for context preservation.
memory-manager
Persistent project memory using SQLite + FTS5 + BM25. Fast, zero dependencies (stdlib only), production-ready. Progressive disclosure with 3 layers (compact/index/detailed).