mise

mise is a cursor rule for Cursor from extsoft/elegant-git. It costs 304 tokens per session, scanned A, original, MIT.

A set of project rules for mise, a tool that runs development commands and manages developer tools. It specifies which tasks agents may run, such as fixing code and building output.

In plain words
What is it for?
It is for formatting and autofixing code, building the project, listing available tasks, and previewing documentation.
Why use it?
It prevents agents from running maintainer-only or unsuitable commands in the repository.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It is for formatting and autofixing code, building the project, listing available tasks, and previewing documentation.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/extsoft/elegant-git/mise
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.

Clone the repo
git clone --depth 1 https://github.com/extsoft/elegant-git

Made for: Cursor.

Wrote 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.

agentmods badge for mise

README.md
[![agentmods](https://agentmods.dev/badge/rules/extsoft/elegant-git/mise.svg)](https://agentmods.dev/rules/extsoft/elegant-git/mise)
Your own site
<a href="https://agentmods.dev/rules/extsoft/elegant-git/mise"><img src="https://agentmods.dev/badge/rules/extsoft/elegant-git/mise.svg" alt="Measured on agentmods" height="20"></a>
Per session 304 This file is loaded in full into every session.
When invoked 304 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 5.1 $0.00304 $0.00304
Opus 5 $0.00152 $0.00152
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured 3d ago against content hash 9d82eb9817b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mise 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.

.cursor/rules/mise.mdc · 39 lines

What it actually says

mise

Repo root: .config/mise/config.toml. Run mise tasks when you need to see what is available.

For agent work, use only:

Task Use
fix Lint/format/autofix via hk — run after code changes
build Produce dist/eg
docs-preview Serve docs/ locally via Docker (Jekyll)
# ✅ Agent work
mise run fix
mise run build

# ❌ Never for agents (CI/humans only)
mise run check
mise run test
mise run install

release:artifacts and release:github are maintainer-only. Do not run them unless the user explicitly asks.

Do not run go test, go build, or hk check directly unless the user explicitly asks. Prefer mise run fix then mise run build when verification is needed. Humans during development install with mise run install (default ~/.local/bin, falls back to ~/bin; override with INSTALL_DIR).

New tasks: executable *.bash under .config/mise/tasks/ with #MISE description="...", or [tasks.*] in config.toml.

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 · 39 lines · 304 tokens per session scan A 9d82eb9817b8

Subscribe to this mod's changes

mise is a cursor rule published in the GitHub repository extsoft/elegant-git (47 stars, last pushed 5d ago), licensed MIT. It adds 304 tokens to every session, about $0.0015 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 2026-09-03.