ace:verify-work

A command for user acceptance testing, where a person checks that completed software work meets the agreed requirements. It loads the latest plan and summary, shows what changed, and provides a checklist and suggested tests.

In plain words
What is it for?
It is for reviewing changed files, checking planned requirements, starting the application, and manually testing the finished features.
Why use it?
It turns completed work into a concrete review instead of relying on memory or assumptions. This helps reveal issues that automated checks may miss before delivery.

Command

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/agricidaniel/ace-claude-code/verify-work
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/ace-claude-code
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 683 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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00683
Opus 5 $0.00005 $0.00342
Sonnet 5 $0.00002 $0.00137
Haiku 4.5 $0.00001 $0.00068

Measured 3d ago against content hash 3734243386f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ace:verify-work 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.

.ace/commands/verify-work.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Captures issues for fix planning if needed.

Required: @.ace/planning/STATE.md

Load: Latest SUMMARY.md from phases/

1. Load Completed Work

Find most recent SUMMARY.md or use $ARGUMENTS.

Display what was built:

+==============================================================+
|                    VERIFY WORK                               |
+==============================================================+

Plan: [plan_id] - [plan name]
Completed: [date]

Files Created/Modified:
- src/models/user.ts
- src/services/auth.ts
- src/routes/auth.ts

+==============================================================+

2. Verification Checklist

Present from PLAN.md verification criteria:

VERIFICATION CHECKLIST:

Task 1: [Task Name]
- [ ] [Verification step 1]
- [ ] [Verification step 2]

Task 2: [Task Name]
- [ ] [Verification step 1]

Task 3: [Task Name]
- [ ] [Verification step 1]
- [ ] [Verification step 2]

+==============================================================+

3. Guide Testing

SUGGESTED TESTS:

1. Start the application:
   npm run dev

2. Test [Feature 1]:
   [How to test]

3. Test [Feature 2]:
   [How to test]

+==============================================================+

4. Collect Feedback

Use AskUserQuestion:

"Did everything work as expected?" Options:

  • "Yes, all good" -> Mark verified, continue
  • "Found issues" -> Capture issues

If issues found: "Describe the issues you found:" [Free text capture]

5. Handle Results

All Good

+==============================================================+
|                    VERIFICATION PASSED                       |
+==============================================================+

Plan [plan_id] verified successfully.

Next:
- /ace:plan-phase [N]  Continue development
- /ace:progress        Check overall status

+==============================================================+

Read the full file on GitHub · 160 lines

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.

  1. 3d ago First seen · 160 lines · 11 tokens per session scan A 3734243386f8

Subscribe to this mod's changes

ace:verify-work is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 683 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.