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 xiaojiou176-open/campus-copilot --skill openclaw-readonly-consumergit clone --depth 1 https://github.com/xiaojiou176-open/campus-copilotWrote 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/xiaojiou176-open/campus-copilot/openclaw-readonly-consumer)<a href="https://agentmods.dev/skills/xiaojiou176-open/campus-copilot/openclaw-readonly-consumer"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/campus-copilot/openclaw-readonly-consumer/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/xiaojiou176-open/campus-copilot/openclaw-readonly-consumer"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/campus-copilot/openclaw-readonly-consumer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00033 | $0.00582 |
| Opus 5 | $0.00016 | $0.00291 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
openclaw-readonly-consumer 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 11d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw-Style Read-Only Consumer
Use this skill when your local operator/runtime behaves like an OpenClaw-style shell and you want CampusCopilot to stay on the snapshot-first / thin-BFF-first / read-only side.
Think of CampusCopilot as the labeled binder on the desk:
- CampusCopilot provides structured academic context
- your local runtime decides how to consume that context
- CampusCopilot does not become a browser-control plugin or write-capable operator loop
Start with the narrowest path
- If you need cross-site health, provider readiness, read-only ask, or export tools, start with:
pnpm --filter @campus-copilot/mcp-server start
- If you only need one site's snapshot records, use:
pnpm --filter @campus-copilot/mcp-readonly start:<site>
- If you only need local provider status or cited-AI chat on the Campus semantic contract, use:
pnpm start:api
Inputs
- one local snapshot such as
examples/workspace-snapshot.sample.json - one local runtime that can launch stdio commands
- optional support for the same
mcpServersJSON shape used by Codex/Claude-style MCP setups
Recommended flow
- Export a safe snapshot path:
export CAMPUS_COPILOT_SNAPSHOT="$PWD/examples/workspace-snapshot.sample.json"
- Start with the generic MCP server unless you already know you only need one site.
- If your runtime explicitly accepts the same
mcpServersJSON shape, adapt:examples/integrations/codex-mcp.example.jsonexamples/integrations/claude-code-mcp.example.json
- If it does not accept that exact shape, stay with the direct command snippets from:
examples/openclaw-readonly.md
- Keep all claims snapshot-scoped and read-only.
Good fit
- OpenClaw-style local consumers that need one truthful starting recipe
- imported snapshot review without reopening live browser automation
- read-only MCP or local BFF consumption over Campus-owned semantics
Not a fit
- live browser takeover
- posting, replying, or submitting on external sites
- inventing an official plugin or marketplace contract
- hosted autonomy positioning
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.
- 11d ago First seen · 62 lines · 33 tokens per session scan A d17f331a1f34
openclaw-readonly-consumer is a skill published in the GitHub repository xiaojiou176-open/campus-copilot (2 stars, last pushed 10d ago), licensed MIT. It adds 33 tokens to every session and 582 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 2026-08-31.
Other skills, from other repositories
canvas-homework
Check Canvas for outstanding assignments and either surface the assignment, or draft a response in Max's voice. Use whenever Max asks what assignments / homework / coursework he still has to do, asks to pull an assignment's instructions or files from Canvas, or asks to start/draft an assignment. Orchestrates the…
myopenmath
Work a MyOpenMath / IMathAS math homework set that is launched from Canvas — read the questions, compute the answers, fill the boxes, and submit. Use whenever Max points at a MyOpenMath assignment, says a math homework is "in my Canvas", asks to do/finish/check a numbered homework like "2.1" or "2.2/2.3", or when a…
canvas-quiz
Work a Canvas-native quiz (Classic Quizzes) — find it, open the attempt, read every question, save it to output/, fill the answers, and stop short of submitting. Use whenever Max points at a Canvas quiz, asks about a "syllabus quiz" or a quiz he still has to take, asks what a quiz is asking, or when a Canvas…
mylab-pearson
Work a Pearson MyLab / MyLab Statistics / MathXL homework set or quiz — launch it through the popup, read each question, compute, fill the answer boxes, and submit. Use whenever Max points at a MyLab, MyLab Stats, Mastering, MathXL or Pearson assignment, says a stats homework is "in MyLab", asks to do/finish/check a…
crux
Invoke only when the user explicitly mentions $crux. When invoked, analyze papers, coach research, or support consequential decisions by finding the variable that could change the outcome, separating evidence from rhetoric, and controlling how much help to reveal. Do not activate for ordinary paper, research, or…
obsidian-mindset
Build and update Obsidian learning artifacts from user questions. Use when the user wants to learn concepts, decompose requests into task queues, create or revise question notes, generate or adjust concept comparison Canvas files, compress or overwrite a recent standard artifact, convert learning outputs, or route…