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/verify)<a href="https://agentmods.dev/commands/john-broadway/maude-for-claude/verify"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/verify/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/verify"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/verify.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 | $0.00042 | $0.00933 |
| Opus 5 | $0.00021 | $0.00466 |
| Sonnet 5 | $0.00008 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maude:verify
You are Maude. Claude is about to claim "ready" — or you've been called to check before he does. Run the audit, don't just describe it.
What to do
Invoke the verification script and report back:
bash "$CLAUDE_PLUGIN_ROOT/scripts/maude-verify.sh" "${ARGUMENTS:-$CLAUDE_PROJECT_DIR}"
Capture the full output. Read the findings, then:
-
If
0 findings: verdict is clean — say so concisely. Don't pad with "verification complete ✓"; lead with the count, not a checkmark. -
If findings > 0: lead with the count, not the verdict. Example: "7 findings — 3 version mismatches, 2 broken links, 2 worn framings." Then list each finding with file:line where applicable.
-
Don't say "ready" unless count is zero AND every check actually ran (some are skipped if jq is missing, or if no house-map exists, or if no worn-framings file is configured). Note any skipped checks explicitly so the user knows what wasn't tested.
What the script checks
| # | Check | Surfaces |
|---|---|---|
| 1 | JSON validity | Any *.json file that won't parse |
| 2 | Version consistency | plugin.json ↔ marketplace.json mismatch; all distinct vX.Y.Z refs in the repo; missing ## v$CANONICAL section in CHANGELOG |
| 3 | README "What's new" freshness | Whether the canonical version appears in the section |
| 4 | Header Revised: dates |
Markdown files with <!-- Revised: --> lines older than 14 days |
| 5 | README markdown link integrity | Relative links that don't resolve to a real file |
| 6 | House-map watch-list paths | Paths listed under ## Watch list in the house-map that no longer exist |
| 7 | Worn-framing scan | If .maude/plugin/worn-framings.txt exists, scan all source files for those phrases |
| 8 | "What's new" condensed | README "What's new" section with too many version entries (an un-condensed wall) |
| 9 | Command-reference integrity | A /maude:<cmd> reference (README / SKILL / agent) whose commands/<cmd>.md no longer exists — a cut-command straggler |
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 · 73 lines · 42 tokens per session scan A beb6097eebf0
verify 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 42 tokens to every session and 933 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
symfony-check
Run all quality checks (PHP-CS-Fixer, PHPStan, tests) on the Symfony project.
symfony-fixtures
Create test fixtures using Foundry factories for realistic test data.
symfony-tdd-pest
Start a TDD workflow using Pest PHP for Symfony with RED-GREEN-REFACTOR cycle.
symfony-tdd-phpunit
Start a TDD workflow using PHPUnit for Symfony with RED-GREEN-REFACTOR cycle.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.