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 OutlineDriven/outline-driven-development --skill browser-cookie-storegit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/browser-cookie-store)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/browser-cookie-store"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/browser-cookie-store.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 27 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00037 | $0.00860 |
| Opus 5 | $0.00018 | $0.00430 |
| Sonnet 5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
browser-cookie-store 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 yesterday.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser cookie store
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user runs /browser-cookie-store to populate the session cookie store from installed browsers. |
| Authority | Reversible local: writes only the session cookie store from locally installed browser profiles; rollback is undo. No remote mutation; no credential is transmitted off the host. |
| Side effect | The session cookie store, populated from locally installed browser profiles. No remote, paid, published, or deployed mutation. |
| Done | The destination store holds extracted session cookies conforming to its schema and authenticated browsing is ready. |
Inputs
- Installed browsers on the local machine. The user may specify which browsers are present, but at least one must be available.
- The destination cookie store path (supplied by the harness) and its schema (JSON, SQLite, Netscape, or whatever the harness documents).
- Optional: specific browser profiles to include or exclude.
Procedure
- Discover installed browser profiles. Enumerate browsers present on the local machine and locate each one's profile directory. Chromium-based browsers store profiles under
<user-data-dir>/Default,<user-data-dir>/Profile 1, and so on; Firefox stores them under~/.mozilla/firefox/*.default*. Stop if no browser is installed. Done when: the browser and profile list is confirmed non-empty or the stop is reported. - Read and decrypt each browser's local cookie database. Chromium stores cookies in a SQLite file (
Cookies) within the profile directory, encrypted with an OS keychain secret (Keychain on macOS, DPAPI on Windows, kwallet/gnome-keyring on Linux). Firefox stores cookies incookies.sqlite, unencrypted. If a database is locked or the decryption key is unavailable, skip that browser and continue. Done when: each available browser's cookie database is read or marked skipped with the reason. - Extract session cookies only. Filter for cookies whose attributes indicate active sessions: non-expiring or long-lived
HttpOnlycookies carrying authentication tokens. Discard tracking, analytics, and short-lived cookies. Done when: session cookies are extracted from each readable browser or the browser is marked skipped. - Write the extracted session cookies to the destination store conforming to its schema. Map each cookie's name, value, domain, path, secure, httpOnly, sameSite, and expiry attributes into the store's expected format. Write only after at least one browser's cookies are extracted. Done when: the store holds the extracted cookies in the correct schema.
- Keep every read and write on the local host. Never transmit cookies to any remote endpoint. Done when: no network transmission occurred during extraction or write.
- Verify the store contains the imported cookies and report ready. Done when: the store is verified and the ready report is emitted.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · -28 tokens per session 6340f1a5eb34
- 4d ago First seen · 46 lines · 65 tokens per session scan A a432dcb3eb37
browser-cookie-store is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 860 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
browser-testing
Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.
rudder-worktree-preview-maintainer
Use when starting the current Rudder checkout as a temporary managed local preview with a stable URL, readiness check, logs, stop command, and cleanup path for manual inspection of the current branch or worktree.
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
prohibit-bad-habits
Use when a user wants to define patterns the agent should not do. Don't use for remote, credential, publish, deploy, or irreversible changes.
daytona-chrome-cdp
Launch and control standalone Chrome in a Daytona sandbox via CDP. Use for web sign-in, OAuth, Den Web setup, browser-only flows, or when the app should not be driven through Electron CDP.