AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Browser Session

skill-graysurf-agent-kit-browser-session · by graysurf

Record browser-session goals, steps, statuses, and evidence artifacts through the nils-cli browser-session command.

No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-graysurf-agent-kit-browser-session

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-graysurf-agent-kit-browser-session)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
Archived

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Browser Session? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Browser Session

Use this skill when a browser workflow needs a deterministic evidence record for target, goal, executed steps, statuses, and artifacts.

Contract

Prereqs:

  • Use Browser, Chrome, Playwright, or another browser tool to perform the actual browser operations.
  • Choose an explicit output directory, preferably under a project-scoped agent-out run directory.
  • Required released PATH usage: browser-session available on PATH from nils-cli 0.8.4 or newer.
  • Release boundary: 0.8.4 is the release that includes nils-agent-workflow-primitives.
  • Local checkout fallback: Rust/Cargo plus a validated local nils-cli checkout that builds nils-agent-workflow-primitives, used

only when the PATH binary is absent or reports a version older than 0.8.4.

Inputs:

  • init: required --out DIR, --target TEXT, and --goal TEXT; optional --browser TEXT, --force, and --format text|json.
  • record-step: required --out DIR, --action TEXT, and --status pass|fail; optional --expectation TEXT, repeatable

--artifact PATH, and --format text|json.

  • verify / show: required --out DIR; optional --format text|json.

Outputs:

  • Writes browser-session.json under --out DIR.
  • JSON stdout uses versioned schema values such as cli.browser-session.verify.v1.
  • The record schema is browser-session.record.v1.

Exit codes:

  • 0: command succeeded; for verify, session evidence is complete.
  • 1: runtime failure or incomplete session evidence.
  • 64: usage error.

Failure modes:

  • browser-session is unavailable on PATH and no validated local checkout invocation is being used.
  • Evidence directory cannot be created or written.
  • verify finds no recorded steps or at least one failed step.
  • Caller assumes this CLI can drive a browser; use Browser, Chrome, or Playwright for actual automation.

Setup

Required released PATH boundary:

browser-session --version

Use the PATH command when it resolves to nils-cli 0.8.4 or newer.

Local checkout fallback boundary:

cargo run --locked --manifest-path /path/to/nils-cli/Cargo.toml \
  -p nils-agent-workflow-primitives --bin browser-session -- --version

Run the Cargo form from the workflow's target directory. It is only a fallback transport for a validated local checkout when the released PATH binary is absent or too old. Do not mix PATH and local checkout evidence claims without stating which source was used.

Commands

Required released PATH command:

browser-session init --out  --target  --goal  [--format json]
browser-session record-step --out  --action  --status pass|fail [--artifact  ...] [--format json]
browser-session verify --out  [--format json]
browser-session show --out  [--format json]
browser-session completion 

Local checkout fallback command:

cargo run --locked --manifest-path /path/to/nils-cli/Cargo.toml \
  -p nils-agent-workflow-primitives --bin browser-session --  ...

This CLI records session evidence only; it does not replace the browser automation tool that opens pages, clicks, inspects, or screenshots.

Guardrails

  • Do not treat browser-session as an active browser driver; use Browser, Chrome, Playwright, or another browser tool for active work.
  • Do not hand-edit browser-session.json or duplicate schema, redaction, completeness, or JSON envelope logic in skill-local scripts.
  • Do not preserve raw cookies, credentials, auth headers, URL secrets, or unredacted network logs as artifacts.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.