Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/setup-browser-cookiesWrote 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/mishahanin/heading-os/setup-browser-cookies)<a href="https://agentmods.dev/skills/mishahanin/heading-os/setup-browser-cookies"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/setup-browser-cookies/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/mishahanin/heading-os/setup-browser-cookies"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/setup-browser-cookies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 3 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.
- high Privilege Escalation · line 99 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00079 | $0.01506 |
| Opus 5 | $0.00039 | $0.00753 |
| Sonnet 5 | $0.00016 | $0.00301 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
setup-browser-cookies 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Browser Cookies
Import logged-in sessions from your real Chromium-family browser into the workspace
cookie store at outputs/browser/cookies.json. Backed by the workspace-native
reader scripts/utils/chromium_cookies.py (the same decryptor /yt-pulse uses) —
no external binaries.
How it works
scripts/utils/chromium_cookies.py reads and decrypts cookies for a domain directly
from the browser's profile DB, per profile and per browser. The decryption backend is
DPAPI on Windows, libsecret on Linux, and Keychain on macOS. This skill drives it per
domain and assembles a Playwright-compatible outputs/browser/cookies.json.
Steps
1. Determine domain(s) and browser
If the user gave a domain (e.g. /setup-browser-cookies github.com), use it. Otherwise
ask: "Which domain(s) should I import cookies for, and from which browser (brave /
chrome / chromium / edge, default brave)?" Then STOP and wait.
The profile defaults to ClaudeCode; pass --profile "<name>" if the user logs in
under a different Chromium profile.
2. Import the cookies straight into the store
python3 scripts/utils/chromium_cookies.py "<domain>" --browser brave --profile ClaudeCode --store
One command extracts, converts to Playwright objects, and merges into the store,
keeping every other domain already there. It prints a count and nothing else.
--store resolves the cookie-store path itself through the data-root seam, so
this command names no path.
Never pass --values here. It prints live session tokens to stdout, and under
an agent stdout IS the transcript — which the NEVER list below forbids. --values
exists for a human at a private terminal, not for this flow.
If it errors:
No cookies found(exit 1) — the read matched nothing at all. The profile is not logged in to that domain. Ask the user to log in in that browser/profile first. Read this ONLY as an empty profile. The next entry covers a read that found cookies and could not read them. Both cases printed this same line until 2026-08-28, so this entry taught the wrong cause for one of them.N of M cookie(s) could not be decrypted(exit 4) — the cookies are there and unreadable. The reader leaves the store untouched on purpose. A partial import replaces a working session with an incomplete one. The printedcause:lines say which of the cases below applies.App-bound v20 ... not yet supported— Chrome M127+ app-bound encryption. Fall back toyt-dlp --cookies-from-browser bravefor that workflow (documented inreference/vpn-preflight.md).decrypted bytes are not a valid cookie value— the key is wrong for this profile, or the browser changed its storage format again. Do not retry blindly; report it.secretstorage not installed/ locked keyring (Linux) — only v10 cookies decrypt; unlock the keyring (gnome-keyring / kwallet) for v11.
What ships with it
2 files 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.
- 6d ago First seen · 139 lines · 79 tokens per session scan A e0ae6928e4f8
setup-browser-cookies is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 1,506 once invoked, about $0.0004 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
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
scrapling
Scrape sites with stealth browsing and Cloudflare bypass.
har-derived-api-client
Record a site's XHR into a HAR, derive an HTTP client.
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
blocked-page-recovery
Use when a fetch fails: 403/429, paywall, WAF, bot wall.
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…