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/mitodl/ol-infrastructure/agents-mdgit clone --depth 1 https://github.com/mitodl/ol-infrastructureWhat 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 | $0.02163 | $0.02163 |
| Opus 5 | $0.01081 | $0.01081 |
| Sonnet 5 | $0.00433 | $0.00433 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
ol-infrastructure 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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for ol-infrastructure Repository
This is a large-scale infrastructure-as-code monorepo (467 Python files, ~91K lines of code) for managing MIT Open Learning's cloud infrastructure using Pulumi, Packer/PyInfra, and Concourse.
Scoped AGENTS.md files exist inside src/bilder/, src/ol_concourse/, and src/ol_infrastructure/ — read those when working inside those packages. This root file covers repo-wide concerns only.
Quick Start
# Environment setup (one-time)
uv sync
pulumi login s3://mitol-pulumi-state
# Validate your changes
uv run ruff format src/ # Auto-format code
uv run ruff check src/ # Check code quality
uv run mypy src/ # Type check (75s runtime)
uv run pytest tests/ # Run tests
Documentation Index
The AGENTS.md instructions have been organized into focused documents. Read the relevant sections for your task:
📋 Repository Overview
- Repository structure and organization
- Directory layout and purpose
- Environment requirements
- Critical build constraints
Use when: Understanding the codebase structure or finding where code should live
🔨 Build and Validation
- Environment setup and dependency installation
- Linting, formatting, and type checking commands
- Pre-commit hooks and validation checklist
- Common build issues and solutions
Use when: Setting up environment, validating code, or fixing build errors
🔄 Pulumi Workflows → src/ol_infrastructure/AGENTS.md
Directory roles, stack naming, component rules, key helpers, validation. Deep reference: docs/context/03-pulumi-workflows.md
📦 Packer AMI Building → src/bilder/AGENTS.md
Build chain, PyInfra conventions, component reuse, HCL formatting. Deep reference: docs/context/04-packer-bilder.md
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 · 236 lines · 2,163 tokens per session scan A 37029ffda8b2
ol-infrastructure AGENTS.md is an instructions file published in the GitHub repository mitodl/ol-infrastructure (57 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 2,163 tokens to every session, about $0.0108 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 2026-08-30.
Other instructions, from other repositories
infrawise CLAUDE.md
Instructions for Sidd27/infrawise, a project described as: MCP server for AWS infrastructure analysis — DynamoDB, Lambda, SQS, SNS, S3, API Gateway, PostgreSQL, MySQL, MongoDB, Kafka & IaC drift. Works with Claude Code, Cursor, and GitHub Copilot.
terraform-aws-cognito-user-pool CLAUDE.md
Instructions for lgallard/terraform-aws-cognito-user-pool, covering module structure & organization, file organization, code organization principles, terraform best practices and resource creation patterns.
terraform-aws-backup CLAUDE.md
Instructions for lgallard/terraform-aws-backup, covering terraform aws backup module - development guidelines, module structure & organization, file organization, code organization principles and mcp-powered validation workflow.
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
cdkd CLAUDE.md
Claude Code instructions for go-to-k/cdkd, covering claude.md, project overview, architecture, build and test commands and build (using vite+ / tsdown).
claude-aws-cost-saver CLAUDE.md
Instructions for prajapatimehul/claude-aws-cost-saver, covering aws cost optimization system, quick start, list all checks, view specific check and see required aws cli commands.