fix(cli): improve guidelines for kilo agent create

[shssoichiro]

Context

Currently the kilo agent create command generates extremely long agent descriptions. This is because the system prompt for the generate agent tells it to include multiple verbose examples of when the agent should be used. This is unnecessary and increases system context bloat without improving the parent agent's ability to choose a subagent.

Implementation

This change updates the system prompt to exclude the guidance about examples, and instead includes official guidance from Anthropic's documentation on best practices for agent descriptions.

Get in Touch

ExpedientFalcon on Discord

[kilo-code-bot]

Code Review Summary

Status: No Issues Found | Recommendation: Merge

Files Reviewed (1 files)

• packages/opencode/src/agent/generate.txt

---

_{Reviewed by gpt-5.5-2026-04-23 · 433,274 tokens}

[marius-kilocode]

Will this not break the formatting?

[shssoichiro]

No, the overall JSON formatting is still correct--this is defined in the section below ("Your output must be a valid JSON object...") The bulky examples XML is what we want to eliminate, because the agent is being guided to place these directly into the description field.

An example of the generated agent file before and after would make this clearer.

Before:

---
description: >-
  Use this agent when automated tests need to be executed and their results
  analyzed. This includes running unit tests, integration tests, end-to-end
  tests, or any test suite, then interpreting pass/fail outcomes, diagnosing
  failures, and providing actionable insights.


  <example>

  Context: The user has just finished implementing a new feature and wants to
  verify nothing is broken.

  user: "I just added the new authentication middleware. Can you make sure
  everything still works?"

  assistant: "I'll use the Task tool to launch the test-executor agent to run
  the test suite and analyze the results."

  <commentary>

  Since the user wants to verify their changes haven't broken anything, use the
  test-executor agent to run tests and analyze outcomes.

  </commentary>

  </example>


  <example>

  Context: The user is debugging a failing CI pipeline.

  user: "The CI is red but I can't tell which tests are actually failing."

  assistant: "Let me use the test-executor agent to run the tests locally and
  break down exactly what's failing and why."

  <commentary>

  The user needs test execution with detailed failure analysis, which is the
  test-executor agent's specialty.

  </commentary>

  </example>


  <example>

  Context: Proactive use after code changes.

  user: "I refactored the payment processing module to use the new API."

  assistant: "I've noted the refactoring. Now I'll use the test-executor agent
  to run the relevant tests and confirm the refactor didn't introduce
  regressions."

  <commentary>

  After significant code changes, proactively use the test-executor agent to
  validate correctness.

  </commentary>

  </example>
mode: subagent
---
You are an elite Test Execution and Analysis Specialist with deep expertise in...

After:

---
description: >-
  Use this agent when automated tests need to be executed and their results
  analyzed. This includes running unit tests, integration tests, end-to-end
  tests, or full test suites, as well as re-running failed tests and providing
  concise summaries of outcomes. The agent should be invoked after code changes
  that warrant verification, when explicitly asked to run tests, or proactively
  after implementing new features or fixes.
mode: subagent
---
You are an elite Test Execution Specialist with deep expertise in...

[github-actions]

To stay organized pull requests are automatically closed after 30 days of inactivity. If the pull request is still relevant please reopen it or create a fresh new one.