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 rules/ontorata/ratary/agent-forgegit clone --depth 1 https://github.com/ontorata/rataryWhat 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 | $0.00257 | $0.00257 |
| Opus 5 | $0.00129 | $0.00129 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
agent-forge 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 yesterday.
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
Agent Forge (mandatory)
Before any design, code, test, or review work:
- Identify pipeline stage from docs-ai agent-forge workflows / product phase README under docs-ai · NOW.md
- Read and follow the matching skill in
.cursor/skills/forge-*/SKILL.md(skills remain in the Ratary Cursor workspace) - Run Recall at session start (
forge-recall) and Remember at session end (forge-remember) when MCP is available - Do not skip Intent → Isolate → Blueprint for non-trivial features (multi-file or structural)
- On failure, switch to
forge-diagnosebefore guessing fixes
Authority: docs-ai Knowledge OS > Agent Forge > ad-hoc prompts.
Legacy prompt IDs: search docs-ai designs/ / governance/ — do not duplicate long prompt text in chat.
Constitution: no agent runtime code in Ratary src/ — Forge is workflow law only.
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.
- yesterday First seen · 20 lines · 257 tokens per session scan A 5789c75f77c6
agent-forge is a cursor rule published in the GitHub repository ontorata/ratary (1 stars, last pushed 22d ago), licensed MIT. It adds 257 tokens to every session, about $0.0013 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.