Borrowing it
Nothing to install: this file belongs to andrewstellman/octobatch. 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/andrewstellman/octobatch/main/AGENTS.mdgit clone --depth 1 https://github.com/andrewstellman/octobatchWrote 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/andrewstellman/octobatch/agents-md)<a href="https://agentmods.dev/instructions/andrewstellman/octobatch/agents-md"><img src="https://agentmods.dev/badge/instructions/andrewstellman/octobatch/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 5.1 | $0.01871 | $0.01871 |
| Opus 5 | $0.00936 | $0.00936 |
| Sonnet 5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
octobatch 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Octobatch is a batch processing orchestrator for LLM APIs. It transforms expensive real-time API operations into efficient batch workflows across Gemini, OpenAI, and Anthropic. Written in Python 3.11+, it features a TUI dashboard built with Textual, expression steps using asteval for deterministic computation, fan-out steps for one-to-many pipeline branching, cross-run analysis tooling, and multi-step pipelines with automatic validation and retry.
Setup
git clone https://github.com/andrewstellman/octobatch.git
cd octobatch
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
API keys are set as environment variables: GOOGLE_API_KEY (Gemini), OPENAI_API_KEY (OpenAI), ANTHROPIC_API_KEY (Anthropic). Keys can be placed in a .env file in the project root (see .env.example); the orchestrator and TUI load it automatically via python-dotenv.
Virtual environment
Important: Before running any Python commands, always check for and activate the existing virtual environment. All dependencies are already installed there — do not pip install packages manually.
# Activate the existing venv (do this first!)
source .venv/bin/activate
If .venv does not exist, create it with the Setup instructions above.
Build & test
# Run all tests (venv must be active)
pytest tests/
# Run tests with coverage
pytest tests/ --cov=scripts --cov-report=term-missing
# Run the quality playbook functional tests
pytest quality/test_functional.py -v
# Validate a pipeline config without running it
python3 scripts/orchestrate.py --validate-config --config pipelines/Blackjack/config.yaml
# Run a pipeline (realtime mode, small test)
python3 scripts/orchestrate.py --init --pipeline DrunkenSailor --run-dir runs/test --repeat 10 --realtime --provider gemini --yes
# Generate a pipeline report
python3 scripts/orchestrate.py --report --run-dir runs/test
python3 scripts/orchestrate.py --report --json --run-dir runs/test
# Re-validate failures without API calls
python3 scripts/orchestrate.py --revalidate --run-dir runs/test
# Restart a running orchestrator
python3 scripts/orchestrate.py --restart --run-dir runs/test
# Name a run
python3 scripts/orchestrate.py --name "My Experiment" --run-dir runs/test
# Compare runs side by side
python3 scripts/orchestrate.py --compare runs/run1 runs/run2
# Launch the TUI
python3 scripts/tui.py
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 First seen · 144 lines · 1,871 tokens per session scan A d976ca5732e3
octobatch AGENTS.md is an instructions file published in the GitHub repository andrewstellman/octobatch (10 stars, last pushed 5mo ago), licensed MIT. It adds 1,871 tokens to every session, about $0.0094 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
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.