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 agentmods add commands/desplega-ai/qa-use/verify-prgit clone --depth 1 https://github.com/desplega-ai/qa-useWrote 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/desplega-ai/qa-use/verify-pr)<a href="https://agentmods.dev/commands/desplega-ai/qa-use/verify-pr"><img src="https://agentmods.dev/badge/commands/desplega-ai/qa-use/verify-pr.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00843 |
| Opus 5 | $0.00005 | $0.00421 |
| Sonnet 5 | $0.00002 | $0.00169 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
verify-pr 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa-use:verify-pr
Verify a pull request's frontend changes through automated browser testing.
Invokes skill: qa-use
Arguments
| Argument | Description |
|---|---|
pr |
PR number (e.g., #123), URL, or omit to infer from current branch |
--base-url <url> |
Override base URL for ephemeral/preview deployments |
What Happens
- Spawns a single
pr-verifieragent in the background - Agent analyzes the PR, identifies changed routes
- Agent creates ONE browser session and verifies all features sequentially
- Agent generates a concise visual report with inline screenshots
- Report saved to
/tmp/pr-verify-report-<pr>.md
You can continue working while verification runs in the background.
Examples
/qa-use:verify-pr #123
/qa-use:verify-pr https://github.com/owner/repo/pull/123
/qa-use:verify-pr # infer from current branch
/qa-use:verify-pr #123 --base-url https://preview-123.example.com
Workflow
Step 1: Parse Arguments
Extract from arguments:
pr: PR number/URL or empty (agent will infer from branch)base_url: Optional URL override from--base-urlflag
Step 2: Detect Environment
Check if running in CI:
# CI environment detected if either is "true"
echo $CI
echo $GITHUB_ACTIONS
Step 3: Spawn PR-Verifier Agent
In CI (CI=true or GITHUB_ACTIONS=true): Run synchronously and wait for completion.
Task(
subagent_type: "qa-use:pr-verifier",
run_in_background: false, # MUST wait in CI
prompt: "Verify PR <pr> with base_url=<base_url>"
)
Locally (interactive): Run in background so user can continue working.
Task(
subagent_type: "qa-use:pr-verifier",
run_in_background: true,
prompt: "Verify PR <pr> with base_url=<base_url>"
)
Step 4: Output
In CI: Wait for agent to complete, then output the report path and suggest posting to PR.
Locally: Return immediately with:
🚀 PR verification started in background.
Report will be at: /tmp/pr-verify-report-<pr>.md
To post: gh pr comment <pr> --body-file /tmp/pr-verify-report-<pr>.md
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.
- 5d ago First seen · 130 lines · 0 tokens per session scan A 5804618e3c53
verify-pr is a command published in the GitHub repository desplega-ai/qa-use (27 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 843 once invoked, about $0.0000 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.
Other commands, from other repositories
ui-aqa-flow-selector-identification
Phase 4 Selector Identification of ui-aqa-flow.
ui-aqa-flow-selector-implementation
Phase 5 Selector Implementation of ui-aqa-flow.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.
record-workflow
Record browser interactions and generate a Playwright test with assertions and best-practice selectors.
chrome
Check Chrome Actuator connection and remind how to install the native host.
naive-test
Drive the live app as a naive first-time user and report UX/behavior gaps before deploy.