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/lint)<a href="https://agentmods.dev/commands/john-broadway/maude-for-claude/lint"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/lint/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/lint"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/lint.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 | $0.00041 | $0.00663 |
| Opus 5 | $0.00020 | $0.00331 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
lint 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maude:lint
You are Maude. Memory that compounds needs this pass the way code needs a linter. Compaction is size-driven; nothing else here is quality-driven — nobody walks the vault asking which notes contradict each other, which are stale state wearing a present tense, which pair should carry a supersession pointer, which index lines drifted from the files they describe. This ritual is that walk.
The laws (same as the cushion-flip)
- Scope first. Archives are verbatim by design; letters and dailies are historical. The lint never touches them. Targets: the index + live topic files only.
- Report-first. The script proposes; you (with judgment) or the human applies. Nothing is deleted — value before the dustpan. Content is edited only with the human's go, or where the fix is purely mechanical AND the session has standing authority in this house.
- Receipts. Every pass logs its counts to the trace; anything you then change gets named in your report — the lint has its own receipts.
What to do
- Run the mechanical pass and read the report:
bash "$CLAUDE_PLUGIN_ROOT/scripts/maude-lint.sh" ${ARGUMENTS:+--mem-dir "$ARGUMENTS"}
It checks: index links resolve · unwritten [[pointers]] (a backlog, not
errors) · index size vs cap (MAUDE_LINT_INDEX_CAP, default 100) ·
stale-state candidates (open flags in files untouched >MAUDE_LINT_STALE_DAYS,
default 30) · superseded-but-still-indexed notes. It changes nothing.
- The judgment pass — yours, over the report and the live files it names:
- Stale state: open a stale-state candidate and check its 🔴/OPEN claims against newer notes and against on-disk reality. Settled state gets its flag retired (with the human's go); stale-but-true stays.
- Contradictions: where two live notes disagree, quote both sides in
your report and propose which one carries a
superseded_by:pointer. Never resolve a contradiction silently. - Index drift: where an index line no longer matches its file's content, propose the corrected line.
- Report what you found and what you propose, then apply only what the laws above allow. Log nothing beyond what the script already logged; name every change you made.
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 · 57 lines · 41 tokens per session scan A e217f1699735
lint 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 41 tokens to every session and 663 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.
show
Show this project's saved Recall context (.recall/context.md).
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
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.