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 instructions/alejooroncoy/campus-cli/agents-mdgit clone --depth 1 https://github.com/alejooroncoy/campus-cliWrote 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/instructions/alejooroncoy/campus-cli/agents-md)<a href="https://agentmods.dev/instructions/alejooroncoy/campus-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/alejooroncoy/campus-cli/agents-md.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 | $0.01258 | $0.01258 |
| Opus 5 | $0.00629 | $0.00629 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
campus-cli AGENTS.md 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- campus-cli CLAUDE.md — 92% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
campus-cli — Agent Guide
This CLI/MCP server gives agents direct access to a student's university campus systems. Today only Blackboard Learn (UPC Aula Virtual) is implemented — all its tools use the blackboard_ prefix. Use it to help students check their courses, assignments, grades, and download materials — all without opening a browser. (Future: canvas_*, moodle_* for other universities — not implemented yet.)
Setup
Before using any tool, the user must be authenticated:
campus login # opens browser for Microsoft SSO
campus whoami # verify session is active
If you get Not authenticated, ask the user to run campus login.
Primary workflow
1. blackboard_list_courses → find the relevant courseId
2. blackboard_list_assignments <courseId> → see pending tasks + due dates
3. blackboard_get_grades <courseId> → check current grades
4. blackboard_list_contents <courseId> → browse course materials
5. blackboard_list_contents <courseId> <parentId> → navigate into a subfolder
6. blackboard_list_attachments <courseId> <contentId>→ find downloadable files
Feedback workflow
1. blackboard_get_assignment_feedback <courseId> → scores + instructor comments + feedback files for all assignments
2. blackboard_download_feedback_file <ids> → download an annotated file the professor attached to the grade
Agent behavior rules
- Always confirm before submitting (
blackboard_submit_attempt). Show the user what will be submitted and ask for confirmation. The server also requires direct MCP elicitation and fails closed when the client cannot show it.blackboard_save_attempt_draft(saving progress without sending) does not need this confirmation — only the final submit does. - Downloads are sandboxed — MCP downloads go under
~/Downloads/campus-cli(or the user-configuredCAMPUS_DOWNLOAD_DIR).outputDiris a relative subdirectory, never an arbitrary path, and existing files are not overwritten. blackboard_save_attempt_draft/blackboard_submit_attemptonly work on file/text/link-submission columns — not on quiz-style columns with interactive questions (both look identical fromblackboard_list_assignments, since Ultra treats tests and assignments as the sameresource/x-bb-asmt-test-linkcontent type). If Blackboard returns400with a message like "Attempts cannot be created for assessments with non-presentation-only questions", that column is actually a quiz/test — tell the user, don't retry. A403 bb-rest-attempt-past-due-exceptionis expected/normal once the due date has passed and late attempts aren't allowed — same as the web UI would show, not a bug.- Show grades in context — when showing grades, also show the assignment name, max score, and due date if available.
- Navigate content recursively — if the user asks for materials, explore subfolders using
blackboard_list_contentswithparentId. - Use
blackboard_raw_apifor anything not covered — it is restricted to/learn/api/public/.POST,PUT,PATCH, andDELETErequire direct user confirmation through MCP elicitation. - Session errors are recoverable — if you get a session error, tell the user to run
campus login(not a fatal error). - Respect rate limits — don't fan out more than 5 parallel API calls.
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.
- 3d ago First seen · 85 lines · 1,258 tokens per session scan A 958405a641f6
campus-cli AGENTS.md is an instructions file published in the GitHub repository alejooroncoy/campus-cli (9 stars, last pushed 5d ago), licensed ISC. It adds 1,258 tokens to every session, about $0.0063 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 instructions, from other repositories
generative-ai-for-beginners AGENTS.md
Instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
designing-real-world-ai-agents-workshop CLAUDE.md
Instructions for iusztinpaul/designing-real-world-ai-agents-workshop, covering project, project structure, tech stack, access documentation and running qa.
ThreadShelf CLAUDE.md
Instructions for ChrystianSchutz/ThreadShelf: This project's agent guidance lives in AGENTS.md — read it.
Pass-LLM-with-LLM AGENTS.md
Instructions for Tenstu/Pass-LLM-with-LLM, covering agents.md, project contract, harness engineering rules, runtime modes and session start.