Borrowing it
Nothing to install: this file belongs to Koroqe/OPOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Koroqe/OPOS/main/.claude/skills/serve-console/SKILL.mdgit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/serve-console)<a href="https://agentmods.dev/skills/koroqe/opos/serve-console"><img src="https://agentmods.dev/badge/skills/koroqe/opos/serve-console.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00021 | $0.00935 |
| Opus 5 | $0.00010 | $0.00467 |
| Sonnet 5 | $0.00004 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
serve-console scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
serve-console
When to use
When a human wants a CRM-style read-only view over the company OS — tasks, agents, skills, departments, history — without going through Claude Code or the gh CLI for each lookup. The console is a long-running foreground command; the user stops it with Ctrl-C.
Inputs
port— TCP port to bind. Default:8765(memorable; outside common-conflict ranges).host— bind address. Default:127.0.0.1(loopback only). Pass0.0.0.0to expose on the LAN — WARNING: anyone on your LAN can then read every markdown file in this repo, including restricted folders (company/strategy/). Only do this on a trusted network.open_browser— bool, defaulttrue. When true, auto-opens the URL in the default browser after the server starts.
Steps
-
Resolve repo root.
REPO_ROOT=$(git rev-parse --show-toplevel). -
Verify
ui/console.pyexists. If absent, ABORT with: "ui/console.py not found — runcopier updateto pull v0.3.0+ files, or scaffold a fresh consumer withcopier copy gh:Koroqe/OPOS." -
Verify Python ≥3.10.
python3 --versionparsed asPython 3.X.Y; abort if X<3 or (X==3 and Y<10) with the install hint for your platform. -
Verify dependencies importable.
python3 -c "import jinja2, markdown". Ifmarkdownis missing, ABORT with: "markdownlibrary required:pip install markdown(orpipx inject copier markdownif Copier is your only Python tool)." Do NOT auto-install — touching the user's Python env is a Rule 4 architectural decision per.claude/rules/error-recovery.md. -
Announce + open browser. Print:
OPOS Console serving at http://<host>:<port>/ (Ctrl-C to stop). Ifopen_browser=true, runpython3 -m webbrowser "http://<host>:<port>/"(non-blocking; failure to open the browser is non-fatal). -
Exec the server.
python3 ui/console.py --port <port> --host <host>(add--no-browserifopen_browser=false). Foreground process; KeyboardInterrupt (Ctrl-C) shuts it down cleanly.
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 · 56 lines · 21 tokens per session scan A 76162cf0ff7e
serve-console is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 935 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.
visual-verify-ui
Wraps the browser tool into a dedicated visual QA testing skill for frontend work.
web_scraper
Scrape and extract content from web pages. Supports extracting text, links, headings, and structured data. Use when the user asks to read a web page, extract information from a URL, or scrape website content.
easy-api-mcp
Teaches AI agents how to connect to the open-wa hosted MCP surface via Easy API.
react-component-testing
Applies the three-tier test taxonomy for React applications: unit tests for hooks and pure logic, component tests for behavior and interactions, and end-to-end tests for user flows. Uses Vitest, React Testing Library, and Playwright while focusing on observable behavior over implementation details.