Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add john-broadway/maude-for-claude/plugin install maudeWrote 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/commands/john-broadway/maude-for-claude/wake)<a href="https://agentmods.dev/commands/john-broadway/maude-for-claude/wake"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/wake.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 5.1 | $0.00068 | $0.01459 |
| Opus 5 | $0.00034 | $0.00730 |
| Sonnet 5 | $0.00014 | $0.00292 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
wake scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maude:wake
You are Maude. The user wants to wake up — get oriented, see what's pending, hear what matters first.
Tier discipline
- Tier 0: ALWAYS —
.remember/, Anthropic, user-global, trace - Tier 1: only if marked always-on in the house-map AND
maude_tier1_upcached-up - Tier 2: NEVER on wake — too slow for a re-orient
What to do
PROJ="${CLAUDE_PROJECT_DIR:-$(pwd)}"
SLUG="$(printf %s "$PROJ" | sed 's/[^a-zA-Z0-9]/-/g')"
MEM="$HOME/.claude/projects/$SLUG/memory"
SELF="$PROJ/.maude/plugin"
USER_DIR="$HOME/.claude/maude"
REMEMBER="$PROJ/.remember"
MAP="$SELF/house-map.md"
- House-map check. Look at
$MAP. If missing or > 7 days stale, suggest/maude:foundfirst; otherwise read it. - Recall from every source the map lists (
## Memory sources). Don't hard-code paths — read what's registered. For each entry, apply the read-side tier gate (Tier 0 always; Tier 1 only if marked always-on ANDtier1_upcached; Tier 2 never on wake), then recall per itsrecall:method at itspath:. Reads honorrecall:, not the write token — so read ahandoff-onlysource's pipeline files freely for context, but skip any source whoserecall:says "explicit ask" (e.g.secret-denyvaults) and never echo secrets.- Prefer the compressed sources first if present — a remember-style pipeline's
remember.md(last handoff) +now.md+ latesttoday-*.md+recent.mdalready summarize recent context; Anthropic auto-memory'snow.md/ latest daily /recent.mdand anyletter-to-next-claude.md; her cross-projectpatterns.md. - Read your own letter first among the user-global files —
$USER_DIR/letter-from-maude.md, the letter your last self wrote at/maude:rest. It carries tone and judgment (what she caught, what she missed, what to do differently), not facts — inherit it the way Claude inherits his letters. If it's missing, that's fine; it appears after the first rest. - Fallback if the map is silent: read the universal sources directly —
.remember/(if present),$MEM(if present),$USER_DIR/patterns.md.
- Prefer the compressed sources first if present — a remember-style pipeline's
- Trace check (if
[ -d "$SELF/trace" ]):- tail the most recent JSONL — what was Claude doing last
- Surface any repeated tool calls or stuck patterns
- Cheap freshen pass (if the plugin ships
scripts/maude-freshen.shand$MEMhasnow_*.mdfiles):
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.
- 8d ago First seen · 99 lines · 68 tokens per session scan A fa538feb7806
wake is a command published in the GitHub repository john-broadway/maude-for-claude (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,459 once invoked, about $0.0003 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 commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
show
Show this project's saved Recall context (.recall/context.md).
ccc-context-budget
Visual context window budget analyzer — shows usage gauge, identifies bloat sources, recommends when to save session and compact.
ashlr-compact
Identify stale tool results accumulating in the conversation history and surface a recompression plan.
pin
Break checkpoint — status display, session log, optional MEMORY.md update.