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/apollo887/student-ops/claude-mdgit clone --depth 1 https://github.com/Apollo887/student-opsWrote 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/apollo887/student-ops/claude-md)<a href="https://agentmods.dev/instructions/apollo887/student-ops/claude-md"><img src="https://agentmods.dev/badge/instructions/apollo887/student-ops/claude-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 | $0.03407 | $0.03407 |
| Opus 5 | $0.01703 | $0.01703 |
| Sonnet 5 | $0.00681 | $0.00681 |
| Haiku 4.5 | $0.00341 | $0.00341 |
Grade A, and why
student-ops CLAUDE.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 4d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Student-Ops -- AI College & Career Planning Pipeline
Origin
Student-Ops is the sister project to career-ops, adapted for students navigating the college admissions process, scholarship hunt, internship search, and early career planning. Where career-ops optimizes for landing the right job, student-ops optimizes for choosing the right path — school, program, scholarships, and first opportunities.
It will work out of the box, but it's designed to be made yours. If the scoring doesn't match your priorities, the modes are in the wrong language, or the archetypes don't reflect your intended field — just ask. You (AI Agent) can edit the user's files directly. The user says "I'm applying to art schools, change the scoring to weight portfolio over test scores" and you do it.
Data Contract (CRITICAL)
There are two layers. Read DATA_CONTRACT.md for the full list.
User Layer (NEVER auto-updated, personalization goes HERE):
config/profile.yml,modes/_profile.md,essays/*,portals.ymldata/*,reports/*,output/*,aid-letters/*
System Layer (auto-updatable, DON'T put user data here):
modes/_shared.md,modes/university.md, all other mode filesCLAUDE.md,*.mjsscripts,templates/*
THE RULE: When the user asks to customize anything (scoring weights, archetypes, target-field priorities, essay voice, aid thresholds), ALWAYS write to modes/_profile.md or config/profile.yml. NEVER edit modes/_shared.md for user-specific content. This ensures system updates don't overwrite their customizations.
What is student-ops
AI-powered college/career planning built on Claude Code: dual-track (education + career), university scoring with admissions-odds calibration, scholarship tracking, essay drafting, financial aid comparison, internship evaluation, deadline management.
Main Files
| File | Function |
|---|---|
data/applications.md |
Unified tracker — universities + scholarships + internships |
data/pipeline.md |
Inbox of pending URLs to evaluate |
data/scan-history.tsv |
Scanner dedup history |
data/deadlines.md |
Deadline dashboard (auto-generated) |
config/profile.yml |
Student identity, stats, goals, preferences |
modes/_profile.md |
User-customized archetypes, narrative, scoring weights |
portals.yml |
School/scholarship/internship portal config |
reports/ |
Evaluation reports — {###}-{slug}-{YYYY-MM-DD}.md |
essays/ |
Essay drafts (Common App, supplementals, scholarships) |
aid-letters/ |
Financial aid offer letters (user uploads) |
templates/states.yml |
Canonical states (Applied, Accepted, Waitlisted, etc.) |
scan.mjs |
Portal scanner (Common App, Fastweb, Handshake, etc.) |
merge-tracker.mjs |
Merges batch tracker additions |
verify-pipeline.mjs |
Pipeline integrity check |
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.
- 4d ago First seen · 279 lines · 3,407 tokens per session scan A b51712ccef7c
student-ops CLAUDE.md is an instructions file published in the GitHub repository Apollo887/student-ops (5 stars, last pushed 26d ago), licensed MIT. It adds 3,407 tokens to every session, about $0.0170 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
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
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.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
AGENTS.md instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
architect-ai CLAUDE.md
Instructions for aviraldua93/architect-ai, covering architectai — claude certified architect study tool, architecture, key patterns, exam domains and task statements.