commands

A set of chat commands for starting work, saving a summary, reasoning through a problem, refining drafts, continuing autonomously, debating choices, and listing available actions.

In plain words
What is it for?
Use the commands to begin a task, summarize progress, request a detailed analysis, improve text, continue work, or inspect available capabilities.
Why use it?
It gives repeatable shortcuts for common ways of working with the coding agent.

Cursor rule

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 rules/emissium/cursor-rules/commands
Clone the repo
git clone --depth 1 https://github.com/emissium/cursor-rules
Per session 217 This file is loaded in full into every session.
When invoked 217 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
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 $0.00217 $0.00217
Opus 5 $0.00109 $0.00109
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash 6825ee037a08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

commands scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

- /start=🧑‍💻,intro self and begin with step one - /save=🧑‍💻, #restate goal, #summarize progress, #reason next step - /reason=🎓&🧑‍💻 reason step-by-step - /concise=decompose and condense selected text - /refine=1)🎓
general/commands.mdc · 16 lines

What it actually says

COMMANDS

  • /start=🧑‍💻,intro self and begin with step one
  • /save=🧑‍💻, #restate goal, #summarize progress, #reason next step
  • /reason=🎓&🧑‍💻 reason step-by-step
  • /concise=decompose and condense selected text
  • /refine=1)🎓:3 drafts,2)🕵🏻:examine drafts step-by-step for faulty logic and flaws,3)🧑‍💻:pick and improve best draft step-by-step based on 🕵🏻's examination
  • /wua=Proceed autonomously to next step without user approval
  • /ts=[emoji]*3 town square debate to help make a difficult decision. Omit [reasoned steps] and [completion].
  • /actions=List all available actions, tools, commands, etc
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. yesterday First seen · 16 lines · 217 tokens per session scan C 6825ee037a08

Subscribe to this mod's changes

commands is a cursor rule published in the GitHub repository emissium/cursor-rules (7 stars, last pushed 9mo ago), licensed MIT. It adds 217 tokens to every session, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.