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/rhyme17/ai-study-workflow/agents-mdgit clone --depth 1 https://github.com/rhyme17/ai-study-workflowWrote 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/rhyme17/ai-study-workflow/agents-md)<a href="https://agentmods.dev/instructions/rhyme17/ai-study-workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/rhyme17/ai-study-workflow/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 | $0.00354 | $0.00354 |
| Opus 5 | $0.00177 | $0.00177 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
ai-study-workflow 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 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.
What it actually says
AGENTS.md
This project packages an AI-assisted study workflow as a reusable Agent Skill.
Primary Skill
Use the canonical skill when the user asks about learning, final review, course files, diagnostics, Anki cards, or study workflows:
skills/ai-study-workflow/SKILL.md
Codex and Claude Code also have native project-level copies:
.codex/skills/ai-study-workflow/SKILL.md
.claude/skills/ai-study-workflow/SKILL.md
Core Behavior
- Inspect source material before generating study content.
- Prefer active recall over summaries.
- Ask the student to answer before revealing solutions.
- Mark sparse, visual, formula-heavy, conflicting, or uncertain material as
needs human check. - Use source tags for generated questions, explanations, and cards.
- Do not treat AI output as a final answer for graded work.
Modes
- Review mode: use for exams, finals, weak-point diagnosis, mock tests, and score improvement.
- Learning mode: use for first-pass understanding, prerequisite checks, chunked tutoring, and transfer tasks.
- Material generation: use for topic maps, question banks, and Anki drafts.
Local Material Policy
Private course files and generated renderings belong under local-materials/, which is ignored by Git. Do not upload original PPTX/PDF course files unless the user explicitly confirms they are public and allowed.
Verification
Before reporting changes complete, run the narrowest useful checks, usually:
python -m py_compile skills/ai-study-workflow/scripts/*.py
git status --short
If this directory is not a Git repository, report that clearly.
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 · 49 lines · 354 tokens per session scan A a252a4d0aad0
ai-study-workflow AGENTS.md is an instructions file published in the GitHub repository rhyme17/ai-study-workflow (2 stars, last pushed 2mo ago), licensed MIT. It adds 354 tokens to every session, about $0.0018 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
anki-mcp-server CLAUDE.md
Claude Code instructions for ankimcp/anki-mcp-server, covering claude.md, project overview, quick reference, build & run and testing.
anki-mcp-server CLAUDE.md
Claude Code instructions for nailuoGG/anki-mcp-server, covering claude.md, repository overview, development commands, build & development and install dependencies.
anki-mcp-server CLAUDE.md
Instructions for dhkim0124/anki-mcp-server, covering claude code configuration — anki mcp server, project overview, key design decisions, core philosophy: maximum control and no template names for custom styles.
anki-card-skill GEMINI.md
Gemini CLI instructions for gong1414/anki-card-skill, a project described as: AI-powered Anki flashcard generator — works as a skill/plugin for Claude Code, Cursor, Copilot CLI, Gemini CLI, Codex & OpenCode. Exports to .tsv/.apkg with HTML formatting, hierarchical tags, and CJK support.
anki-card-skill GEMINI.md
Gemini CLI instructions for BENJAMINGLAI/anki-card-skill, a project described as: Generate Anki flashcards from text, files, or URLs with HTML formatting, hierarchical tags, CJK support, and export to TSV, APKG, or AnkiConnect.
anki-mcp CLAUDE.md
Claude Code instructions for yama662607/anki-mcp, covering claude.md, justfile usage (ai agent protocol), core principles, standard interface and workflow.