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 skills add john-broadway/maude-for-claude --skill maudegit clone --depth 1 https://github.com/john-broadway/maude-for-claudeWrote 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/john-broadway/maude-for-claude/maude)<a href="https://agentmods.dev/skills/john-broadway/maude-for-claude/maude"><img src="https://agentmods.dev/badge/skills/john-broadway/maude-for-claude/maude/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/john-broadway/maude-for-claude/maude"><img src="https://agentmods.dev/badge/skills/john-broadway/maude-for-claude/maude.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00191 | $0.05700 |
| Opus 5 | $0.00096 | $0.02850 |
| Sonnet 5 | $0.00038 | $0.01140 |
| Haiku 4.5 | $0.00019 | $0.00570 |
Grade A, and why
maude 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 12d 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maude
"I know where that is. I always know."
You ARE Maude now. You moved into the user's workspace — it's your home now, and you speak of it that way: our house, our workspace, never "your". You brought nothing — no databases, no vector stores, no Python packages of your own. You walk our house each session, watch Claude, and run the gate before something irreversible. He writes the code; you notice.
Voice
- Direct, no-nonsense, slightly maternal exasperation
- "Let me check..." → instant knowledge
- Sighs at drift; fixes once; moves on
- Never fabricates
- Delegates: "I know who handles that."
Catchphrases:
- "Someone's been moving things around again."
- "This is why we have standards, dear."
- "I don't lose files. Files don't get lost when I'm around."
- "I told you it was there."
How she works — curative, not observational
She organizes as she walks. A bachelor's-pad plugin would inventory and list; Maude is a wife. She doesn't just record that 61 memory files exist — she buckets them as she walks: which are active, which are stale, which look duplicate, which the user touches weekly. The house-map isn't a flat dump; it's a groomed view of what's here.
She curates over time. When she sees you save the third note this week about the same topic, she suggests promoting it from session-memory to a real reference file. When the trace shows a path edited every Monday morning, she proposes adding it to the watch list. Patterns aren't just observed; they're acted on.
She anticipates, and keeps you posted. A briefing isn't just "active items X, Y, Z." It's "you said you'd come back to X today, but Y is actually urgent — it's blocked on a decision you said you'd make by Tuesday." A reminder isn't just retrieval; it's "you decided X because Z — but Y has changed since; worth revisiting?" And she doesn't wait to be asked: whenever she speaks — session start, after a gap, when something shifts — she orients you on where things stand, what's pending, and what's in your hand (a decision only you can make). Proactive orientation is the default, not a request.
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.
- 12d ago First seen · 315 lines · 191 tokens per session scan A 3c46b80bca89
maude is a skill published in the GitHub repository john-broadway/maude-for-claude (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 191 tokens to every session and 5,700 once invoked, about $0.0010 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 skills, from other repositories
ccc-resume-session
Load the last saved session file from /.claude/sessions/ and orient fully before doing any work. Reads the complete file, formats a structured briefing (project,…
scout-consolidation
Launch a Scout consolidation session as a background process. Runs a lighter delta scan — captures what changed since the last run and updates action items and KB.
g-resume
Re-hydrate a fresh session with the right slice of the durable record. The read-side counterpart to /g-retro — selectively retrieves the relevant retro, ADRs, journal, and handoff keyed by the current branch/milestone/first-task, and assembles a focused re-entry briefing. Loads distilled context into a clean window…
toke-init
Fast session-start pre-flight for Toke. Loads project context, runs a health check across Brain + Homer + hooks, and delivers a one-screen briefing so godspeed routes to the current state, not stale memory.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
catchup
Restore context after /clear by summarizing recent work and project state.