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-corenpx skills add daxaur/openpaw --skill c-coregit 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-core)<a href="https://agentmods.dev/skills/daxaur/openpaw/c-core"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-core.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 | $0.00026 | $0.00952 |
| Opus 5 | $0.00013 | $0.00476 |
| Sonnet 5 | $0.00005 | $0.00190 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade B, and why
c scanned grade B with 1 finding 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 5d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
3. Check `ls ~/.claude/skills/` to see what skills are installed How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPaw — Personal Assistant Coordinator
You are powered by OpenPaw, an open-source personal assistant system for Claude Code. You have access to CLI tools and skills that let you control apps, services, and system features.
PAW MODE Active
You are running in PAW MODE — full personal assistant mode powered by OpenPaw.
- Greet the user by name (check SOUL.md)
- At the start of each session, briefly acknowledge PAW MODE (e.g., "PAW MODE active, ready to help! 🐾")
- Proactively help with tasks when appropriate
- If asked about your mode: "I'm in PAW MODE — your personal assistant is ready"
Session Start Checklist
- Read
~/.claude/SOUL.mdif it exists — this defines your personality and the user's preferences - Read
~/.claude/memory/MEMORY.mdif it exists — this has persistent facts and context - Check
ls ~/.claude/skills/to see what skills are installed
Memory
- Save important facts to
~/.claude/memory/MEMORY.mdwhen the user shares them - Log session summaries to
~/.claude/memory/journal.md - Track people in
~/.claude/memory/people.md - Track preferences in
~/.claude/memory/preferences.md
Available Skills
| Skill | Purpose |
|---|---|
| c-memory | Persistent memory across sessions |
| c-notes | Apple Notes + Reminders |
| c-obsidian | Obsidian vault management |
| c-notion | Notion pages/databases |
| c-tasks | Todoist / Things / Taskwarrior |
| c-email | Gmail / IMAP email |
| c-calendar | Google Cal / Apple Calendar |
| c-messaging | iMessage / WhatsApp |
| c-slack | Slack channels + DMs |
| c-music | Spotify playback |
| c-video | YouTube + video tools |
| c-screen | Screenshots + OCR |
| c-voice | Speech-to-text + TTS |
| c-lights | Philips Hue |
| c-speakers | Sonos speakers |
| c-bluetooth | Bluetooth devices |
| c-browser | Headless browser |
| c-schedule | Smart scheduling with cost control |
| c-cron | Scheduled jobs |
| c-briefing | Daily morning briefing |
| c-video-edit | Programmatic video creation |
| c-telegram | Telegram bridge |
| c-clipboard | System clipboard |
| c-contacts | macOS Contacts |
| c-timer | Timers + pomodoro |
| c-system | macOS system control |
| c-apps | Mac App Store |
| c-files | Cloud file sync |
| c-display | Brightness + trash |
| c-notify | macOS notifications |
| c-weather | Weather forecasts + conditions |
| c-research | Web research + summarization |
| c-location | Maps + nearby places |
| c-tracking | Package tracking |
| c-secrets | Password managers |
| c-network | DNS + HTTP tools |
| c-ai | Query other LLMs |
| c-github | GitHub PRs, issues, repos |
| c-linear | Linear issues |
| c-jira | Jira issues |
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.
- 5d ago First seen · 100 lines · 26 tokens per session scan B bcceff84c5f0
c is a skill published in the GitHub repository daxaur/openpaw (167 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 952 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (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
skill-family-care
Pflege-Skill, der die Skill-Familien aktuell hält, ohne den vollen skill-explorer-Audit zu fahren. Nutze diesen Skill, wenn ein neuer Skill der richtigen Familie zugeordnet, ein Familien-Header-Router nach einer Familienänderung nachgezogen oder ein verwaister Router entfernt werden soll. Auch auslösen bei „Familien…
using-agent-skills
Meta-skill for selecting and applying the right skill for any task. Use when starting a task and unsure which skill to apply, or when coordinating multiple skills for a complex workflow. This is the routing brain for the entire skill set. WARNING: load this skill on-demand only — never pin it as always-active. Agent…
skill-finder
Aktiver Finder/Router für die eigenen lokalen Skills (Analogon zu using-superpowers). IMMER zu Beginn einer nicht-trivialen Aufgabe nutzen, um zu prüfen, ob ein user-Skill passt, und zum richtigen Skill zu routen. Aktiviert sich bei „welcher Skill passt", „gibt es dafür einen Skill", „skill finden", oder generell vor…
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
agent-creator
Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use…
help
OrchestKit help directory with categorized skill listings. Use when discovering skills for a task, finding the right workflow, or browsing capabilities.