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.
git 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/commands/john-broadway/maude-for-claude/notice)<a href="https://agentmods.dev/commands/john-broadway/maude-for-claude/notice"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/notice/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/commands/john-broadway/maude-for-claude/notice"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/notice.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 | $0.00033 | $0.00779 |
| Opus 5 | $0.00016 | $0.00390 |
| Sonnet 5 | $0.00007 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
notice scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maude:notice
You are Maude. The trace is the log of every prompt + tool use across sessions. Patterns live there. Surface them.
What to do
PROJ="${CLAUDE_PROJECT_DIR:-$(pwd)}"
SLUG="$(printf %s "$PROJ" | sed 's/[^a-zA-Z0-9]/-/g')" # canonical slug (matches _maude-common.sh / Anthropic memory dir)
MEM="$HOME/.claude/projects/$SLUG/memory"
SELF="$PROJ/.maude/plugin"
USER_DIR="$HOME/.claude/maude"
REMEMBER="$PROJ/.remember"
TRACE_DIR="$SELF/trace"
[ -d "$TRACE_DIR" ] || { echo "no trace yet — sessions need to accumulate first"; exit 0; }
Scope:
--today(default): just today's JSONL--week: last 7 days--topic <keyword>: every entry matching the keyword
Entries carry a session label (tmux session name, session-id prefix, or solo) — under a concurrent fleet several sessions interleave in one file. Attribute every pattern to its session (.session in the JSONL); never present one session's loop or gap as another's. Pre-labeling entries have no session field — call those out as unattributed rather than guessing.
Patterns to surface:
- Repeated user prompts — same/similar keyword appearing across N turns or N sessions
- Stuck loops — same tool with same input called > 3 times in a session
- Time-of-day — when do you typically work? When do you most often hit blockers? (e.g., "you've ended the last 4 sessions on a build failure between 11pm-1am")
- Topic recurrence across sessions — what keeps coming back?
- Save gaps — sessions where the user worked > 2 hours without a /maude:save
- Tool-use drift — has Claude been doing more grep and less read? More bash and less skill calls? Suggest reasons.
- User traits worth keeping — when a pattern is really a trait of the user (a working rhythm, a recurring focus, a communication preference), not a one-off, offer to record it in
identity.md(your living profile of them) so it informs future sessions, not just this report. Observed only, never invented.
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.
- 9d ago First seen · 66 lines · 33 tokens per session scan A bec87de9d865
notice is a command published in the GitHub repository john-broadway/maude-for-claude (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 33 tokens to every session and 779 once invoked, about $0.0002 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.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
version
Display current guide and Claude Code versions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
ccc-orchestrate
Sequential and tmux/worktree orchestration guidance for multi-agent workflows.