ORG-2 is a local-first application for running coding agents while recording, replaying, and reviewing how they build software. Teams use it to connect requests, agent decisions, actions, and resulting code across sessions and supported agent command-line tools. Its catalogue add-ons provide skills, rules, and instructions for this agent-building workflow.
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 skills add org2AI/ORG2 --skill architecture-auditgit clone --depth 1 https://github.com/org2AI/ORG2Wrote 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/skills/org2ai/org2/architecture-audit)<a href="https://agentmods.dev/skills/org2ai/org2/architecture-audit"><img src="https://agentmods.dev/badge/skills/org2ai/org2/architecture-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/org2ai/org2/architecture-audit"><img src="https://agentmods.dev/badge/skills/org2ai/org2/architecture-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 293 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00070 | $0.15102 |
| Opus 5.5 | $0.00028 | $0.06041 |
| Sonnet 5.5 | $0.00014 | $0.03020 |
| Haiku 4.5 | $0.00007 | $0.01510 |
Grade A, and why
architecture-audit 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 1mo 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 1mo ago First seen · 576 lines · 70 tokens per session scan A ed8e55360fea
architecture-audit is a skill published in the GitHub repository org2AI/ORG2 (2,630 stars, last pushed 8d ago), licensed AGPL-3.0. It adds 70 tokens to every session and 15,102 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
domain-primitives-and-always-valid
A design guide for domain primitives and always-valid domain models: types that validate their values when created and remain valid afterward.
parse-dont-validate
A code-review and design approach that replaces checks which merely report valid or invalid data with typed values that carry the result of the check.
markdown-review
Render a local .md or .markdown file for interactive visual review, discuss line-anchored feedback, and edit the underlying Markdown source. Use when the user wants to preview, review, comment on, or revise rendered Markdown, and automatically after Codex creates or materially edits a local Markdown file unless the…
rust-patterns
A guide to common Rust programming patterns for building safe and maintainable applications. It explains ownership, error handling, traits, generics, concurrency, and how to organize modules and public interfaces.
rust-best-practices
A guide to writing and reviewing idiomatic Rust, a programming language focused on memory safety and speed. It covers ownership, error handling, performance, tests, and documentation.
rust-skills
Comprehensive Rust coding guidelines with 265 rules across 26 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, concurrency, unsafe code, API design, memory optimization, performance, numeric safety, conversions, serde, pattern matching, macros…