What is verify-change?

A verification checklist for AI-written MVP changes that records checks for correctness, security, maintainability, and the delivered result against acceptance-criteria IDs.

Use it before delivery to list changed files and behaviours, map them to acceptance criteria, and record unit, integration, security, and maintainability checks.

It gives a change a documented review record and makes clear which requested behaviours were checked, failed, or did not apply.

How synaptic-ai-consulting/AAMAD configures Claude Code and Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to synaptic-ai-consulting/AAMAD. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/synaptic-ai-consulting/AAMAD/main/.cursor/skills/verify-change/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/synaptic-ai-consulting/AAMAD

Made for: Claude Code, Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/synaptic-ai-consulting/aamad/verify-change/github.svg)](https://agentmods.dev/skills/synaptic-ai-consulting/aamad/verify-change)

Your own site

<a href="https://agentmods.dev/skills/synaptic-ai-consulting/aamad/verify-change"><img src="https://agentmods.dev/badge/skills/synaptic-ai-consulting/aamad/verify-change/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/synaptic-ai-consulting/aamad/verify-change"><img src="https://agentmods.dev/badge/skills/synaptic-ai-consulting/aamad/verify-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 655 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00050	$0.00655
Opus 5.5	$0.00020	$0.00262
Sonnet 5.5	$0.00010	$0.00131
Haiku 4.5	$0.00005	$0.00065

Measured 3d ago against content hash 15aac8f588e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-change 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.

.cursor/skills/verify-change/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Change

Record that the current change set is understood and checked before Deliver. Owned by @qa.eng; invoked as *verify-change. Write the checklist into project-context/2.build/qa.md (section Verification checklist). Do not invent a second QA artifact.

This is not a replacement for *test-unit, *test-integration, *test-visual, *run-evals, or .cursor/skills/product-design/SKILL.md.

Step 1: Load context

Read:

project-context/1.define/prd.md, sad.md, user-stories/*.md, system-description.md (if present)
project-context/2.build/qa.md, frontend.md, backend.md, integration.md
project-context/2.build/ux-review.md and project-context/1.define/ux.md when UI changed
aamad.config.yml (quality.require_verification_checklist, crew.autonomy)

Step 2: Collect the change set

List the files and behaviors this increment shipped. Map each behavior to an acceptance-criteria ID (AC-*) when one exists.

Step 3: Fill the checklist

For the increment, record pass / fail / not applicable with a one-line note:

Check	Result	AC-*	Note
Correctness — unit
Correctness — integration / smoke
Security — no new secrets; tools stay on the SAD allowlist
Maintainability — change stays inside MVP and the recorded pattern
Author explanation — what shipped and why it is safe to release

Rules:

The author (persona that made the change, summarized here by QA) must explain what shipped in the Author explanation row. A passing test suite is not that explanation.
When UI changed, cite ux-review.md in the note. Do not repeat Shape / Implement / Review / Harden and do not treat a matching visual snapshot as proof the design is good.
When the Pattern Decision includes a model call, cite evals.md status. Do not re-run the eval design here.
Fail the checklist if an agent loop, live-state retrieval, or a side-effecting tool appeared that the SAD did not allow.

Read the full file on GitHub · 50 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.

3d ago First seen · 50 lines · 50 tokens per session scan A 15aac8f588e6

Subscribe to this mod's changes

verify-change is a skill published in the GitHub repository synaptic-ai-consulting/AAMAD (88 stars, last pushed 4d ago), licensed Apache-2.0. It adds 50 tokens to every session and 655 once invoked, about $0.0002 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 2026-10-26.

Security Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

AAMAD: Skill for Claude Code