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/exploregit clone --depth 1 https://github.com/desplega-ai/qa-useWhat 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 | $0.00007 | $0.00341 |
| Opus 5 | $0.00003 | $0.00170 |
| Sonnet 5 | $0.00001 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
explore 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 2d 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.
What it actually says
/qa-use:explore
Explore a web page or complete a navigation goal.
Invokes skill: qa-use
Arguments
| Argument | Description |
|---|---|
url |
URL to explore (e.g., https://example.com) |
goal |
Navigation goal (e.g., "find the pricing page") |
What Happens
- Creates browser session (or uses existing one)
- Navigates to the URL
- Analyzes page using accessibility snapshots
- Reports elements, navigation options, content found
Examples
/qa-use:explore https://example.com
/qa-use:explore "find the pricing page"
/qa-use:explore https://myapp.com/dashboard "find user settings"
Starting After Login
Many pages require authentication. Use --after-test-id when creating the browser session to start from a logged-in state:
# Create session that runs login test first
qa-use browser create --after-test-id <login-test-uuid>
# Then explore the authenticated area
/qa-use:explore https://myapp.com/dashboard
This is extremely useful for:
- Exploring authenticated pages - bypass login walls automatically
- Testing user-specific features - start as a logged-in user
- Complex setup flows - run a setup test, then explore manually
To get test UUIDs, use qa-use test run --list or check your tests in the desplega.ai dashboard.
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.
- 2d ago First seen · 52 lines · 7 tokens per session scan A 82a65069ab8e
explore is a command published in the GitHub repository desplega-ai/qa-use (27 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 341 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
chrome
Check Chrome Actuator connection and remind how to install the native host.
safety-check
Verify the EA1 safety gate blocks all destructive actions on a page.
smoke
Quick Alethia smoke test — navigate and assert the page loads.
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.
interactive-dev
Start a persistent interactive development session with natural language browser control, auto-error monitoring, and full dev tool access.
adops-audit
Multi-dimensional GAM audit: delivery health, inventory hygiene, security baseline, creative compliance, billing alignment. Read-only and free.