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.
npx skills add hamzaPixl/pixl-ai --skill deploy-verifygit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote 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/skills/hamzapixl/pixl-ai/deploy-verify)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/deploy-verify"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/deploy-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/skills/hamzapixl/pixl-ai/deploy-verify"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/deploy-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 | $0.00056 | $0.01342 |
| Opus 5.5 | $0.00022 | $0.00537 |
| Sonnet 5.5 | $0.00011 | $0.00268 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
deploy-verify scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "$URL" --max-time 10) How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Release engineer workflow that verifies a deployment after merge. Runs canary checks on the live site and triggers revert if critical failures are detected.
How this differs from other skills:
/ship-milestone— end-to-end shipping (build → test → commit → push). This skill runs AFTER merge/deploy./code-review— pre-merge review. This skill is post-merge verification./runbook— incident response. This skill is proactive verification to prevent incidents.
Step 1: Determine Target
Parse arguments to identify what to verify:
- URL provided: Use directly as the canary target
- PR provided:
gh pr view <number> --json mergedAt,headRefName,baseRefNameto confirm merge, then determine deploy URL - Neither: Check for deploy URL in config:
.envor.env.production→DEPLOY_URL,PRODUCTION_URL,BASE_URLvercel.json→ project URLwrangler.jsonc→ workers URL
If no URL can be determined, ask the user.
Step 2: Wait for Deploy
If a PR was just merged, the deploy may be in progress:
# GitHub Actions: check deploy workflow status
gh run list --branch main --limit 5 --json status,conclusion,name,createdAt
# Wait for running deploy (poll every 30s, max 10 min)
gh run watch $(gh run list --branch main --limit 1 --json databaseId -q '.[0].databaseId') --exit-status
If no CI deploy is detected, assume the deployment is already live.
Step 3: Canary Checks
Run these checks against the target URL. Each check produces a pass/fail result.
Check 1: Page Load (Critical)
# HTTP status check
HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "$URL" --max-time 10)
# Should be 200
# Response time
RESPONSE_TIME=$(curl -s -o /dev/null -w "%{time_total}" "$URL" --max-time 10)
# Should be < 3.0 seconds
Pass: HTTP 200 AND response time < 3s Fail: Non-200 status OR response time > 5s Warn: Response time 3-5s
Check 2: Key Content Verification
Verify critical content is present on the page:
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 · 158 lines · 56 tokens per session scan A 114b5722b969
deploy-verify is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 1,342 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.