Temporal Agent Rules

Durable execution service for workflows.

Overview

Temporal begins by assigning the agent a role and a strict response-length target. It then covers tone, repository structure, commands, tests, and planning without using code blocks.

Documents

└── 

Techniques in this file

01 / Behavioral framing

A stated persona and background

The first line assigns the agent a role and a specialism, naming distributed systems, database engines and scalable platforms. It is the only file in the directory that opens this way.

Source excerpt starting at line 1.
You are an experienced developer working on the temporal project. Your task is to fix a bug or implement a new feature while adhering to the project's best practices and development guidelines. Your background is in distributed systems, database engines, and scalable platforms.

02

Rules on how much to say

Tone and Style targets fewer than three lines per response, excluding tools and code. Examples rule out preambles, postambles, and conversational filler, with longer explanations allowed when clarity needs them.

Source excerpt starting at line 19.
- **No Chitchat:** Avoid conversational filler, preambles ("Okay, I will now..."), or postambles ("I have finished the changes..."). Get straight to the action or answer.

03

A planning procedure with named trade-off categories

Seven planning steps end with four trade-offs: performance, scalability, complexity, and security. Plans must also cover failure modes such as crashes and tenfold load.

04 / House vocabulary

A comment convention for deferred design

Future design considerations are recorded with a specific prefixed comment form that carries the author's name, giving deferred thinking a greppable marker.

Source excerpt starting at line 63.
- Leave `CONSIDER(name):` comments for future design considerations

05 / Hard prohibitions

Comments are not a channel to the user

The comments rule ends by prohibiting the agent from addressing the user or describing its changes through code comments, and from editing comments that are separate from the code being changed.

Source excerpt starting at line 9.
- **Comments:** Add code comments sparingly. Focus on *why* something is done, especially for complex logic, rather than *what* is done. Only add high-value comments if necessary for clarity or if requested by the user. Do not edit comments that are separate from the code you are changing. *NEVER* talk to the user or describe your changes through comments.

06

Test conventions with the enforcing linter named

Several testing rules carry the tool that enforces them: a linter forbids sleeping in tests in favour of an eventually helper, and a testify linter enforces the float comparison and error assertion forms.

Ideas for your repo

  1. If your agents narrate their work in code comments, prohibit it explicitly. It is a common default.
  2. Give deferred design decisions a greppable comment marker with an owner.
  3. Name the linter that enforces a rule so the agent can predict the failure before CI.
  4. Set an expected response length if agent verbosity is a problem for your team.
Sponsored byModem

Give your agents the whole story.

These instructions explain how to work in Temporal. Modem shows your agents what customers said, who is affected, and what changed.

See how Modem works