PAUL is a structured development workflow for Claude Code that organizes AI-assisted work into planning, implementation, and state-reconciliation steps. It is for developers who want acceptance criteria, managed context, and completed plans while building software with Claude Code. Its catalogue entries are commands that implement the workflow.
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/ChristopherKahler/paulWrote 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/christopherkahler/paul/verify)<a href="https://agentmods.dev/commands/christopherkahler/paul/verify"><img src="https://agentmods.dev/badge/commands/christopherkahler/paul/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/christopherkahler/paul/verify"><img src="https://agentmods.dev/badge/commands/christopherkahler/paul/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 | $0.00014 | $0.00508 |
| Opus 5.5 | $0.00006 | $0.00203 |
| Sonnet 5.5 | $0.00003 | $0.00102 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
paul: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 1mo 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.
What it actually says
When to use: After completing a plan, validate that what Claude built actually works from the user's perspective.
Who tests: The USER performs all testing. Claude generates the test checklist, guides the process, and captures issues.
<execution_context>
@/.claude/paul-framework/workflows/verify-work.md
@/.claude/paul-framework/templates/UAT-ISSUES.md
</execution_context>
@.paul/STATE.md @.paul/ROADMAP.md
The workflow implements:
- Identify test scope (specified or most recent SUMMARY)
- Extract testable deliverables from SUMMARY.md
- Generate test checklist based on acceptance criteria
- Guide user through each test via AskUserQuestion
- Collect and categorize any issues found
- Log issues to phase-scoped UAT file
- Present summary with verdict
- Offer next steps based on results
<success_criteria>
- Test scope identified from SUMMARY.md
- Checklist generated based on deliverables
- User guided through each test
- All test results captured (pass/fail/partial/skip)
- Any issues logged to
.paul/phases/XX-name/{plan}-UAT.md - Summary presented with verdict
- User knows next steps based on results </success_criteria>
<anti_patterns>
- Don't run automated tests (that's for CI/test suites)
- Don't make assumptions about test results — USER reports outcomes
- Don't skip the guidance — walk through each test
- Don't dismiss minor issues — log everything user reports
- Don't fix issues during testing — capture for later </anti_patterns>
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.
- 1mo ago First seen · 61 lines · 14 tokens per session scan A f7ce85afcf7f
paul:verify is a command published in the GitHub repository ChristopherKahler/paul (1,253 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 508 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
test-suite
Run comprehensive test suite with coverage analysis.
fix
Correction automatisee des bugs identifies par la QA Recette.
a11y-audit
Audit Accessibilité WCAG 2.2 AAA.
recette
Tests d'acceptance automatises avec Claude in Chrome.