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 agentmods add skills/longbkit/clisbot/architectnpx skills add longbkit/clisbot --skill architectgit clone --depth 1 https://github.com/longbkit/clisbotWhat 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 | $0.00099 | $0.01771 |
| Opus 5 | $0.00049 | $0.00886 |
| Sonnet 5 | $0.00020 | $0.00354 |
| Haiku 4.5 | $0.00010 | $0.00177 |
Grade A, and why
architect 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 2d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
Treat architecture as the traceable assignment of identity, behavior, authority, persistence, lifecycle, and process ownership to clisbot's existing systems. Start from one concrete user flow, prove what the repository executes, and add the smallest coherent extension only when the current owner chain cannot express the job.
Select one mode
State the selected mode and scope before acting. Do not blend modes silently.
- Use
askfor architecture questions, feature exploration, or “how should this work?”. Answer from evidence without editing product code or creating a persistent planning artifact. Default toaskwhen no stronger signal exists. - Use
planwhen the user asks for a plan, proposal, roadmap, design audit, or migration approach. Create or update the appropriate research, feature, audit, or task artifact; do not create an accepted decision or edit product code. - Use
decidewhen the user accepts a proposal, asks to ratify a decision, or requests implementation of an architecture-affecting change. Record each material decision in its repository-level or feature-level decision owner and update canonical architecture when meaning changes. Implement only when the user requests implementation. - Use
autowhen the user delegates the outcome and asks Codex to decide and build without architecture checkpoints. Internally run plan -> decide -> implement for each material decision, then verify and update artifacts truthfully. Ask only for unresolved scope, authority, destructive action, or an external blocker.
If current contracts and decisions already settle the matter, reuse them. Do not create another decision record merely to restate an existing rule. If no material architecture decision exists, use the normal implementation loop without artifact inflation and say why.
Load only the evidence the task needs
- Always read architecture-routing.md.
- For runtime, session, runner, persistence, credentials, lifecycle, detached process, monitor, HTTP listener, or CLI work, also read runtime-persistence-routing.md.
- Before creating or updating a plan, decision, feature, or task artifact, read artifact-format.md.
- Read the selected canonical documents and executable owners completely enough
to establish the owner chain. Use
rgto locate moved owners rather than trusting cached paths.
What ships with it
4 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.
- 2d ago First seen · 174 lines · 99 tokens per session scan A 304ed9308d8c
architect is a skill published in the GitHub repository longbkit/clisbot (114 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 1,771 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
canvas
Display HTML content on connected OpenClaw nodes (Mac app, iOS, Android).
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
node-connect
Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale…