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 elevanaltd/HestAI-MCP --skill vercel-previewgit clone --depth 1 https://github.com/elevanaltd/HestAI-MCPWrote 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/elevanaltd/hestai-mcp/vercel-preview)<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/vercel-preview"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/vercel-preview/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/elevanaltd/hestai-mcp/vercel-preview"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/vercel-preview.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 | $0.00022 | $0.01398 |
| Opus 5 | $0.00011 | $0.00699 |
| Sonnet 5 | $0.00004 | $0.00280 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
vercel-preview 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -I -H "x-vercel-protection-bypass: $VERCEL_AUTOMATION_BYPASS_SECRET" \ How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===VERCEL_PREVIEW=== META: TYPE::SKILL VERSION::1.0 STATUS::ACTIVE COMPRESSION_TIER::AGGRESSIVE DOMAIN::HEPHAESTUS[tool_crafting]⊕HERMES[automation]
§1::PURPOSE
Enable automated access to Vercel protected preview deployments for CI/CD, UI validation, and E2E testing
§2::PROTECTION_BYPASS_PATTERN
METHOD::Protection_Bypass_for_Automation
SECRET_NAME::VERCEL_AUTOMATION_BYPASS_SECRET
SECRET_LOCATIONS::[
vercel_dashboard::"Project Settings -> Deployment Protection -> Auto-injected",
github_secrets::"Repository Settings -> Secrets -> Actions",
local_dev::".env.local[GITIGNORED]"
]
ACCESS_METHODS::[
HTTP_HEADER::"x-vercel-protection-bypass: ${VERCEL_AUTOMATION_BYPASS_SECRET}",
QUERY_PARAM::"?x-vercel-protection-bypass=${VERCEL_AUTOMATION_BYPASS_SECRET}"
]
§3::CI_WORKFLOW_INTEGRATION
§4::GITHUB_ACTIONS_PATTERN
# .github/workflows/ci.yml
jobs:
integration-tests:
runs-on: ubuntu-latest
steps:
- name: Wait for Vercel Preview
uses: patrickedqvist/[email protected]
id: vercel
with:
token: ${{ secrets.GITHUB_TOKEN }}
max_timeout: 300
- name: Run E2E Tests
env:
VERCEL_PREVIEW_URL: ${{ steps.vercel.outputs.url }}
VERCEL_AUTOMATION_BYPASS_SECRET: ${{ secrets.VERCEL_AUTOMATION_BYPASS_SECRET }}
run: npm run test:e2e
§5::PLAYWRIGHT_CONFIGURATION
// playwright.config.ts
import { defineConfig } from '@playwright/test';
export default defineConfig({
use: {
baseURL: process.env.VERCEL_PREVIEW_URL,
extraHTTPHeaders: {
'x-vercel-protection-bypass': process.env.VERCEL_AUTOMATION_BYPASS_SECRET || '',
},
},
});
§6::CHROME_DEVTOOLS_MCP_ACCESS
CHROME_DEVTOOLS_PATTERN::[
// Navigate with bypass query param
mcp__chrome-devtools__navigate_page(
url: "${VERCEL_PREVIEW_URL}?x-vercel-protection-bypass=${SECRET}"
),
// OR set header via evaluate_script before navigation
mcp__chrome-devtools__evaluate_script(
function: "() => { /* custom fetch with header */ }"
)
]
§7::SETUP_CHECKLIST
PREREQUISITES::[
1::vercel_pro_plan_or_higher[automation_bypass_is_paid_feature],
2::deployment_protection_enabled[Project_Settings->Deployment_Protection],
3::automation_bypass_generated[generates_VERCEL_AUTOMATION_BYPASS_SECRET]
]
CONFIGURATION::[
1::add_to_github_secrets[repository_settings->secrets->actions],
2::add_to_local_env[.env.local_for_local_testing],
3::update_ci_workflow[pass_secret_to_test_steps],
4::configure_playwright[extraHTTPHeaders_or_query_param],
5::verify_access[curl_with_header_returns_200]
]
VERIFICATION_COMMAND::
curl -I -H "x-vercel-protection-bypass: $VERCEL_AUTOMATION_BYPASS_SECRET" \
https://your-preview-url.vercel.app
# Should return 200, not 401/403
§8::SECURITY_CONSIDERATIONS
NEVER::[
commit_secret_to_git,
log_secret_in_CI_output,
share_secret_in_documentation,
use_secret_in_client_side_code
]
ALWAYS::[
use_github_secrets_for_CI,
use_gitignored_.env.local_for_local,
rotate_if_exposed,
limit_to_preview_deployments[not_production]
]
ROTATION::[
location::"Vercel Dashboard -> Project -> Settings -> Deployment Protection",
action::"Regenerate secret",
update::"GitHub Secrets + local .env.local"
]
§9::TROUBLESHOOTING
ISSUE::401_Unauthorized_despite_bypass[
CHECK::[
secret_correct_and_not_stale,
header_name_exact["x-vercel-protection-bypass"],
secret_passed_to_env_in_CI,
not_trying_production_URL[bypass_for_previews_only]
]
]
ISSUE::Preview_not_found[
CHECK::[
PR_created_and_pushed,
vercel_integration_enabled,
wait_for_deployment_complete[use_wait-for-vercel-preview_action]
]
]
ISSUE::Bypass_not_available[
CHECK::[
vercel_plan[Pro_or_higher_required],
deployment_protection_enabled_first,
feature_may_require_team_admin
]
]
§10::AGENT_INTEGRATION
UI_VALIDATOR_USAGE::[
RECEIVES::[preview_url, acceptance_criteria],
ACCESSES::preview_via_bypass_header,
VALIDATES::visual+functional_requirements,
RETURNS::PASS/FAIL+evidence
]
CI_PIPELINE_USAGE::[
TIER_1::quality_gates[no_preview_needed],
TIER_2::preview_integration[uses_bypass_for_E2E],
PATTERN::wait_for_preview->export_url->run_tests_with_bypass
]
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 · 198 lines · 22 tokens per session scan A 29292fd3e690
vercel-preview is a skill published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 1,398 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other skills, from other repositories
azure-microsoft-playwright-testing-ts
Run Playwright tests at scale using Azure Playwright Workspaces (formerly Microsoft Playwright Testing). Use when scaling browser tests across cloud-hosted browsers, integrating with CI/CD pipelines, or publishing test results to the Azure portal.
playwright-ci
Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.
playwright-testing
E2E testing with Playwright - Page Objects, cross-browser, CI/CD.
azure-microsoft-playwright-testing-ts
Run Playwright tests at scale using Azure Playwright Workspaces (formerly Microsoft Playwright Testing). Use when scaling browser tests across cloud-hosted browsers, integrating with CI/CD pipeline...
Checkly Monitoring as Code
Teach agents to build synthetic monitoring as code with Checkly, including Playwright browser checks, API checks, alerting, and CI deploy workflows.
CI Test Sharding Parallelization
Teach agents to shard and parallelize Playwright, Jest, and pytest suites in CI to reduce wall-clock time while merging reports reliably.