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/agentproto/tsnpx agentmods add skills/agentproto/ts/bureauWrote 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/agentproto/ts/bureau)<a href="https://agentmods.dev/skills/agentproto/ts/bureau"><img src="https://agentmods.dev/badge/skills/agentproto/ts/bureau/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/agentproto/ts/bureau"><img src="https://agentmods.dev/badge/skills/agentproto/ts/bureau.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 Privilege Escalation · line 165 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 Data Exfiltration · line 66 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 75 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00131 | $0.03642 |
| Opus 5.5 | $0.00052 | $0.01457 |
| Sonnet 5.5 | $0.00026 | $0.00728 |
| Haiku 4.5 | $0.00013 | $0.00364 |
Grade A, and why
bureau 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 1mo 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 -s http://127.0.0.1:8830/health # {"ok":true,"tools":26} How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bureau — the installable browser capability server
Quick start: bureau start
bureau start orchestrates headless Camofox + bureau serve in a single
command.
bureau start # Camofox :9377 + serve :8830, foreground
bureau start --detach # everything in the background, exit 0 if healthy
bureau start bureau-only # Camofox assumed up, starts just serve
bureau start --port 9000 # bureau serve on :9000
bureau start --camofox-port 9400 --detach
bureau start --camofox-cmd "camoufox serve --port 9377" --detach
bureau start --timeout 90 # max delay 90 s (default 60)
Camofox command resolution (in order): --camofox-cmd →
$CAMOFOX_SERVE_CMD → launchctl start com.agentik.camofox (macOS). If
nothing resolves, explicit error with instructions. Idempotent: if Camofox is
already up, it is not respawned.
Bureau is the standalone, shipped product of the browser stack: one daemon
co-located with a stealth Firefox (Camofox), exposing browser capabilities as
MCP-over-HTTP plus a CLI. Same daemon runs three ways behind one
BureauEndpoint contract — bureau serve on the user's machine (this skill),
agentproto-daemon-managed, or as a cloud RuntimeSpec on a Guilde
browser-workstation. Zero @guilde deps; it's its own appliance.
Layout
- App:
projects/browser/apps/bureau— the CLI + serve entrypoint (@agstudio/bureau,bin: bureau). - Invoke:
node projects/browser/apps/bureau/dist/index.js <cmd>(built output), orpnpm --filter=@agstudio/bureau dev <cmd>(tsx watch), or the globalbureaubin if linked. - State:
~/.agentproto/bureau/—sessions/(saved identities, the cookie store),guilde.json(connection),runtime.json(descriptor when hosted). Secrets (platform passwords, gld_ tokens) live in the OS Keychain, never on disk or argv. - Ports: daemon
:8830(MCP/mcp+/watch/<tab>screencast +/health); Camofox REST:9377.
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.
- 1mo ago First seen · 280 lines · 131 tokens per session scan A 2d13170e9665
bureau is a skill published in the GitHub repository agentproto/ts (10 stars, last pushed today), licensed Apache-2.0. It adds 131 tokens to every session and 3,642 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
demo-recorder
Use when the user wants a scripted screen-recording demo video of a web app, a narration script or text-to-speech voice-over for one, or a dubbed cut.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
browser-tools
Safety rules over the upstream agent-browser skill (scraping ethics, auth, request pacing, local URLs). URL policy is the Claude Code sandbox's job when the operator enables it. Use for browser automation.
qa-screenshot
Screenshot a page (deploy preview or a dev server on localhost) in the sandbox's headless Chromium, look at it, and embed it in a task comment. Use to verify a visual change or record before/after evidence.
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).