Borrowing it
Nothing to install: this file belongs to adamwstauffer/shidler. 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/adamwstauffer/shidler/main/AGENTS.mdgit clone --depth 1 https://github.com/adamwstauffer/shidlerWrote 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/adamwstauffer/shidler/agents-md)<a href="https://agentmods.dev/instructions/adamwstauffer/shidler/agents-md"><img src="https://agentmods.dev/badge/instructions/adamwstauffer/shidler/agents-md/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/instructions/adamwstauffer/shidler/agents-md"><img src="https://agentmods.dev/badge/instructions/adamwstauffer/shidler/agents-md.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 | $0.03062 | $0.03062 |
| Opus 5.5 | $0.01225 | $0.01225 |
| Sonnet 5.5 | $0.00612 | $0.00612 |
| Haiku 4.5 | $0.00306 | $0.00306 |
Grade A, and why
shidler 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 8d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents (Claude Code, Codex CLI, and any other tool that reads this
convention) working in this repository. CLAUDE.md is a one-line pointer here — the same
AGENTS.md-canonical convention students follow in their portfolio repos.
Working Principles
Adapted from Andrej Karpathy's coding guidelines for this docs/Markdown repository:
- Think before editing — state assumptions and surface ambiguity instead of guessing silently; offer the simpler option when one exists.
- Simplicity first — do the task that was asked; no speculative restructuring of courses, templates, or decision memos.
- Surgical changes — touch only what the request needs, and preserve each file's existing style and formatting (existing template conventions always win). Flag stray issues you notice rather than fixing them unasked; when records document a past change (e.g. a decision memo), update live materials, not the record.
- Goal-driven — define what "done" looks like, then verify it:
recalc.pyreturns 0 errors, generated Office files validate, referenced paths resolve, no broken links.
Repository Purpose
Unified portfolio and course materials hub for Shidler College of Business (University of Hawaiʻi at Mānoa) courses taught by Adam W. Stauffer. Contains syllabi, assignment frameworks, project templates, branded materials, and professional portfolio documents — all managed via Git/Markdown.
Student-facing tutorials live on the companion Kumu site, https://adamwstauffer.github.io/ai-lms/. This repo's stage briefs and the site's stage pages are kept in sync — a change to one usually implies a change to the other.
Repository Structure
courses/— Subject-first directories (e.g.,courses/International-Corporate-Finance/), not course-code-first. Seecourses/README.mdfor the Shidler-code-to-directory map. Each subject directory shares one shape:projects/<slug>/(shared curriculum) + one<CODE[-POPULATION]>/subfolder per offering (e.g.,BUS-629-VEMBA/,FIN-321/). Seedocs/decisions/2026-07-08-generic-course-directory-naming.mdfor the full rationale.docs/— Centralized documentation hub:_branding/— Adam's personal slide and color kit: design tokens (design.json), visual reference (design-system.html),.potxtemplates. Not an official UH or Shidler asset.decisions/— One public memo,2026-07-08-generic-course-directory-naming.md; other memos are kept privately, seeCHANGELOG.mdai-usage-guidelines.md,writing-style-guide.md,reproducibility-playbook.md,grading-scale.md,financial-model-assumptions.md
templates/(repo root) — Deliverable templates students copy (memo, spec, case brief, stage brief, prompt log,portfolio/,spreadsheets/)- How-to setup (GitHub, AI tools) lives on Kumu onboarding: https://adamwstauffer.github.io/ai-lms/onboarding.html
CHANGELOG.md— Notable changes to how the repo is organized- The instructor bio, resume and CV live on the site, never in this repo: https://adamwstauffer.github.io/bio.html
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.
- 8d ago Changed · +27 tokens per session 43718b64f3ff
- 21d ago Changed · +2 lines · +65 tokens per session f277516abce4
- 23d ago Changed · +30 tokens per session 4fd1ba5740ee
- 24d ago Changed · -21 lines · -814 tokens per session 09df1d859e0c
- 1mo ago Changed · +10 lines · +232 tokens per session e6426eafa1f9
- 1mo ago First seen · 175 lines · 3,522 tokens per session scan A 0f6372f9ee41
shidler AGENTS.md is an instructions file published in the GitHub repository adamwstauffer/shidler (10 stars, last pushed 3d ago), licensed MIT. It adds 3,062 tokens to every session, about $0.0122 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.