Index of every page on this site: llms.txt
All skills
vercel-labs avatar

/vercel

@5aad200 official
by Vercel Labsvercel-labs/agent-browser53k stars
3,714
Run it yourself

Access and test Vercel deployments with agent-browser, behind Deployment Protection or at a different feature flag variant. Use when a preview or production URL redirects to a Vercel login page, returns a protection 401 or 403, needs short-lived Trusted Sources OIDC authentication instead of a static bypass secret or public exception, or must be viewed with a Vercel feature flag set to another variant.

Use this Skill: https://skilld.dev/gh/vercel-labs/agent-browser/vercel

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈103 tokens for metadata: the name and description. ≈2.7k when used: this file.

Description uses 5.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈414 characters, or 5.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Vercel deployments

Reach a Vercel deployment as the user asked to see it without changing what anyone else sees. Pass protection and flag overrides on this browser's requests; changing project settings or a flag's served variant needs explicit approval.

Deployment Protection

Use the caller's existing Vercel identity and a short-lived OIDC token. Do not disable Deployment Protection, make the deployment public, or ask for a static bypass secret first.

Same-project preview

A local development token for the target project can access that project's protected Preview deployments through the default Trusted Sources self-access rule. No Trusted Sources configuration is normally required.

Confirm the local identity and Vercel CLI version:

vc whoami
vc --version

Require Vercel CLI 53.3.0 or newer before running vc project token. Versions 50.25.0 through 53.2.x write the token to stderr, so command substitution captures nothing and the credential can appear in logs. If the installed version is older, stop and ask the user to upgrade it. Do not attempt to capture or recover the token from stderr.

Set the target project and scope explicitly. If they cannot be inferred safely, ask the user. In a directory whose existing .vercel/project.json link has been verified against the target, vc project token without a project name is also valid. Do not run vc link merely to get an OIDC token: current Vercel CLI versions also pull development variables into .env.local when linking.

Create a named browser session, mint a development OIDC token with the Vercel CLI, then inject it without printing or persisting it:

export AGENT_BROWSER_SESSION="$(agent-browser session id --scope worktree --prefix vercel-preview)"
export VERCEL_PREVIEW_URL="https://my-app.vercel.app"
export VERCEL_PROJECT="my-app"
export VERCEL_SCOPE="my-team"

(
  TOKEN="$(vc project token "$VERCEL_PROJECT" --scope "$VERCEL_SCOPE")"
  test -n "$TOKEN"
  agent-browser open "$VERCEL_PREVIEW_URL" --headers \
    "{\"x-vercel-trusted-oidc-idp-token\":\"$TOKEN\"}"
)

agent-browser snapshot -i

Continue the normal workflow in that same session. If your harness runs each command in a new shell, the exported AGENT_BROWSER_SESSION is gone afterwards, so pass the same name with --session on later commands. The header is scoped to the target origin and applies to the document, scripts, styles, fonts, and in-page requests. If the browser session is closed or restarted, repeat the authenticated open command.

Never print the token, paste it into source, or save it in an environment file.

Other environments and callers

Trusted Sources configuration is needed when:

  • a local development token must reach a protected Production deployment;
  • the caller belongs to another Vercel project or team;
  • the target project's self-access rules were customized; or
  • Vercel returns TRUSTED_SOURCES_ENVIRONMENT_MISMATCH.

There is no supported Vercel CLI or public REST API for editing Trusted Sources rules. An authorized human must open the target project's Settings → Deployment Protection → Trusted Sources and add only the required caller and environment mapping. A local token has the development environment, so protected Production access requires development to production.

Stop and hand off the exact rule to the human. Do not use browser automation to change access control, and do not broaden unrelated environment mappings. Retry the authenticated open after the human confirms the rule is saved.

Human intervention boundaries

The same-project development to Preview path should run without human intervention when the Vercel CLI is already authenticated and the target project and scope are known. A human is needed only when:

  • the Vercel CLI has no authenticated identity and no existing VERCEL_TOKEN; interactive vc login requires the user;
  • the installed Vercel CLI is older than 53.3.0 and must be upgraded before token minting;
  • the correct target project or scope cannot be inferred safely for token minting;
  • a Trusted Sources rule must be added or changed; the dashboard is the only supported management surface, and this changes access control;
  • Secure Backend Access with OIDC Federation was disabled on the calling project and must be re-enabled in Settings → Security; or
  • the static-secret fallback must be enabled or rotated and the agent needs explicit authorization for that access-control change. After approval, the agent can use vc project protection instead of requiring dashboard interaction.

The agent can diagnose each case and state the exact action required, then continue after the user confirms completion.

Use the correct header

Send the Vercel-issued token as:

x-vercel-trusted-oidc-idp-token: <VERCEL_OIDC_TOKEN>

Do not substitute x-vercel-oidc-token. That header carries workload identity into a Vercel Function; it does not authenticate an inbound request through Deployment Protection.

Diagnose failures

  • Redirect to vercel.com/login: Deployment Protection did not accept the request.
  • TRUSTED_SOURCES_ENVIRONMENT_MISMATCH: the token is valid, but its caller environment cannot reach the target environment.
  • Application 401 or 403 after protection passes: debug the application's own authentication separately.
  • Application 404 on a deliberately missing route: the request passed Deployment Protection and reached the application.

Static-secret fallback

Use Protection Bypass for Automation only when OIDC is not viable or the tool cannot send the Trusted Sources header. Enabling or rotating it changes access control, so obtain explicit authorization first. Create a dedicated secret so it can be rotated independently, keep it in an environment variable, and pass it as a header:

vc project protection enable <project> --protection-bypass \
  --protection-bypass-secret "$VERCEL_AUTOMATION_BYPASS_SECRET"

agent-browser open "$VERCEL_PREVIEW_URL" --headers \
  "{\"x-vercel-protection-bypass\":\"$VERCEL_AUTOMATION_BYPASS_SECRET\",\"x-vercel-set-bypass-cookie\":\"true\"}"

The cookie directive creates a reusable _vercel_jwt cookie. Treat saved browser state containing that cookie as a credential.

Feature flags

To view a variant other than the one an environment serves, set an override cookie in this browser. Do not use vc flags set, enable, disable, split, or rollout to view a variant, because they change it for everyone using the environment.

Flags declared with flag() from the Flags SDK apply overrides from the vercel-flag-overrides cookie. The cookie value is encrypted with the FLAGS_SECRET of the environment under test. Find the flag key and its variants in the source or with vc flags inspect <flag>, then mint the cookie without printing the secret. Pulling the secret with --project and minting with vc flags override both require Vercel CLI 56.3.0 or newer; if the installed version is older, ask the user to upgrade it. Each environment has its own FLAGS_SECRET, so set VERCEL_ENVIRONMENT to the environment that serves the URL under test, such as preview or production. Set VERCEL_PREVIEW_URL, VERCEL_PROJECT, and VERCEL_SCOPE as in Same-project preview, including for a deployment without protection; the block stops when any of them is missing.

The mint encrypts the cookie locally with vc flags override; no package install or registry access is needed. That command reads FLAGS_SECRET from the environment or a .env file in its working directory, so the block points it at an empty temporary directory to keep a project .env.local from supplying a different secret, and takes the last line of its output, which is the cookie value.

(
  set -e
  : "${AGENT_BROWSER_SESSION:?set it to the session of the protected open}"
  : "${VERCEL_ENVIRONMENT:?set it to the environment that serves the URL}"
  : "${VERCEL_PREVIEW_URL:?set it to the deployment URL}"
  : "${VERCEL_PROJECT:?set it to the target project}"
  : "${VERCEL_SCOPE:?set it to the target team scope}"
  ENV_FILE="$(mktemp)"
  vc env pull "$ENV_FILE" --environment "$VERCEL_ENVIRONMENT" \
    --project "$VERCEL_PROJECT" --scope "$VERCEL_SCOPE" --yes >/dev/null
  PULLED="$(grep '^FLAGS_SECRET=' "$ENV_FILE" | cut -d= -f2- | tr -d '"')"
  rm "$ENV_FILE"
  case "$PULLED" in
    "" | "[SENSITIVE]") ;;
    *) FLAGS_SECRET="$PULLED" ;;
  esac
  case "$FLAGS_SECRET" in
    "" | "[SENSITIVE]") echo "FLAGS_SECRET is not readable; ask the user for it" >&2; exit 1 ;;
  esac
  MINT_DIR="$(mktemp -d)"
  OVERRIDE="$(FLAGS_SECRET="$FLAGS_SECRET" vc flags override "my-flag=variant-b" \
    --cwd "$MINT_DIR" --non-interactive | tail -n 1)"
  rm -rf "$MINT_DIR"
  test -n "$OVERRIDE"
  agent-browser --session "$AGENT_BROWSER_SESSION" cookies set vercel-flag-overrides "$OVERRIDE" --url "$VERCEL_PREVIEW_URL"
  agent-browser --session "$AGENT_BROWSER_SESSION" reload
  agent-browser --session "$AGENT_BROWSER_SESSION" screenshot
)

Run this with the session name of the protected open, and confirm in the screenshot that the requested variant rendered before reporting. The Flags SDK ignores an override it cannot decrypt without raising an error, so a screenshot that still shows the served variant usually means the secret belongs to another environment. agent-browser cookies clear removes the override along with every other cookie, so repeat the protected open after clearing.

If FLAGS_SECRET is stored as a Secret, vc env pull writes the placeholder [SENSITIVE] instead of the value because Secret values are write-only, and the script stops. Ask the user for the FLAGS_SECRET of VERCEL_ENVIRONMENT, export it, and run the script again. A readable value from the pull always takes precedence over an exported one.

If the app evaluates flags without the Flags SDK or through another provider, the cookie has no effect and there is no request-scoped path. Ask the user before changing the flag with vc flags set, record the original variant, restore it afterwards, and verify the restore with vc flags inspect.

Avoid dead ends

  • There is no vercel share CLI command. Shareable Links are intended for people and are not the automation path.
  • vercel curl is useful for HTTP requests, but it cannot render and interact with a page.
  • Changing a flag's served variant to take a screenshot changes it for teammates, CI, and users of that environment. Use the override cookie.
  • Deployment Protection Exceptions make the domain public. Do not use them merely to unblock an agent.
  • Do not expose OIDC tokens, bypass secrets, authenticated URLs, or saved state in logs, screenshots, source files, or user-facing output.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert2d3 checks · Risk SAFE
  • Gen Agent Trust Hub2d

    This skill provides a secure framework for accessing protected Vercel deployments. It emphasizes the use of short-lived OIDC tokens over static secrets and includes specific logic to prevent credential leakage caused by older CLI versions. These security considerations are well-integrated into the skill's core functionality.

  • Socket2d

    No alerts

  • Snyk2d

    Risk: CRITICAL · 2 issues

Signed by skilld at 5aad200. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 1 hour ago.

Activeupdated last week
What it can do
Runs commands
All 4 allowed tools
Bash(agent-browser:*)Bash(npx agent-browser:*)Bash(vc:*)Bash(vercel:*)

README badge

README badge for vercel-labs/agent-browser/vercel