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/jzjzzzzzzz/intentforge/agents-mdgit clone --depth 1 https://github.com/jzjzzzzzzz/IntentForgeWrote 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/jzjzzzzzzz/intentforge/agents-md)<a href="https://agentmods.dev/instructions/jzjzzzzzzz/intentforge/agents-md"><img src="https://agentmods.dev/badge/instructions/jzjzzzzzzz/intentforge/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 | $0.00207 | $0.00207 |
| Opus 5 | $0.00103 | $0.00103 |
| Sonnet 5 | $0.00041 | $0.00041 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
IntentForge 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 5d 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
Agent Instructions
IntentForge is an intent-preserving CAD project. The first supported model family is wall_mounted_bracket.
Current Phase
Implement only simple, testable Python components for the MVP. Do not add LLM calls, GUI automation, SolidWorks/Fusion/FreeCAD control, broad CAD object support, or MCP behavior until those phases are explicitly requested.
Engineering Rules
- Use named parameters for important dimensions.
- Preserve assumptions, unknowns, constraints, feature reasons, and validation checks.
- Keep model-family behavior explicit. Do not silently generalize beyond
wall_mounted_bracket. - Prefer deterministic validation and small data models over clever parsing.
- Add pytest coverage for behavior that could break design intent.
- Fix implementation causes when tests fail. Do not weaken tests to hide failures.
CAD Rules
Future CadQuery generation should create editable parametric models from a feature plan, not one-off visual approximations. Feature steps should map to meaningful construction operations and each step must have a reason.
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.
- 5d ago First seen · 21 lines · 207 tokens per session scan A ceb4191ef12c
IntentForge AGENTS.md is an instructions file published in the GitHub repository jzjzzzzzzz/IntentForge (6 stars, last pushed 25d ago), licensed Apache-2.0. It adds 207 tokens to every session, about $0.0010 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
agentcad CLAUDE.md
Claude Code instructions for jdilla1277/agentcad, covering agentcad, repo identity, development, product contract and validation.
CADCLAW AGENTS.md
AGENTS.md instructions for sunnyday-technologies/CADCLAW, covering agents.md — guidance for ai assistants using cadclaw, what cadclaw is, and what it is not, the core rule: place authored parts, don't generate them, why this rule exists and what you may generate.
circuit-synth CLAUDE.md
Instructions for circuit-synth/circuit-synth, covering claude.md - circuit-synth library development guide, project context, professional quality standards, 🎯 core development philosophy and 1. github issue-driven development.
claude-cad CLAUDE.md
Instructions for 0oKevino0/claude-cad, covering claude-cad — notes for claude code, the clone is the workspace (default), when to suggest a separate project (the alternative), helping someone who just arrived and conventions that differ from what you'd assume.
techdrawai-skills CLAUDE.md
Claude Code instructions for MeltFlexDevs/techdrawai-skills, covering notes for agents working in this repository, layout and rules.
vibe-cading AGENTS.md
AGENTS.md instructions for fa-mc/vibe-cading, covering agents.md — universal agent entry point, universal safety invariants, read this first, repository layout for agents and how to onboard your agent.