A guided manual acceptance-testing workflow, where the user checks whether a recently built feature works from their own perspective. It creates a checklist and records the results and issues.

Use it after building a feature to test its acceptance criteria, report issues, and receive a summary of the testing outcome and next steps.

It turns a completed implementation into explicit pass, fail, partial, or skipped checks, so problems are captured before the work is considered done.

paul:verify — Command for coding agents by ChristopherKahler: A guided manual acceptance-testing workflow, where the user checks…

Install

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.

agentmods

npx agentmods add commands/christopherkahler/paul/verify

Clone the repo

git clone --depth 1 https://github.com/ChristopherKahler/paul

Wrote this? Show the measurements

A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.

README.md

[![agentmods](https://agentmods.dev/badge/commands/christopherkahler/paul/verify.svg)](https://agentmods.dev/commands/christopherkahler/paul/verify)

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 508 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00014	$0.00508
Opus 5	$0.00007	$0.00254
Sonnet 5	$0.00003	$0.00102
Haiku 4.5	$0.00001	$0.00051

Measured 3d ago against content hash f7ce85afcf7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

src/commands/verify.md · 61 lines

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>

Changes

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.

3d ago First seen · 61 lines · 14 tokens per session scan A f7ce85afcf7f

Subscribe to this mod's changes

paul:verify is a command published in the GitHub repository ChristopherKahler/paul (1,212 stars, last pushed 12d ago), licensed MIT. It adds 14 tokens to every session and 508 once invoked, about $0.0001 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 2026-08-30.

Testing ai-development ai-tools claude claude-code development-framework project-orchestration

paul:verify

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

safe-refactor

security-review

test

implement-spec

refactor

deploy_to_docker