stet

A safety-evaluation tool for checking whether changes made by an AI coding system are safe to release. It can assess model comparisons, instructions, policies, tools, reasoning, runtime changes, and repository tests.

In plain words
What is it for?
Use it to set up evaluations, build datasets, benchmark coding-agent behaviour, and decide whether to promote or roll back a change.
Why use it?
It helps detect regressions and unsafe changes before they are rolled out.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/stet-ai/stet-cli/stet
Any agent
npx skills add Stet-AI/stet-cli --skill stet
Clone the repo
git clone --depth 1 https://github.com/Stet-AI/stet-cli

Made for: Claude Code, Codex.

Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00116 $0.06323
Opus 5 $0.00058 $0.03161
Sonnet 5 $0.00023 $0.01265
Haiku 4.5 $0.00012 $0.00632

Measured 3d ago against content hash d3b5ffd4b61d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stet 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.

skills/stet/SKILL.md · 389 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

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.

  1. 3d ago First seen · 389 lines · 116 tokens per session scan A d3b5ffd4b61d

Subscribe to this mod's changes

stet is a skill published in the GitHub repository Stet-AI/stet-cli (5 stars, last pushed 7d ago), with no licence file. It adds 116 tokens to every session and 6,323 once invoked, about $0.0006 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.