Skip to content

feat: add Caveman Mode agent and instructions for low-token responses#1498

Open
Philess wants to merge 1 commit intogithub:stagedfrom
Philess:staged
Open

feat: add Caveman Mode agent and instructions for low-token responses#1498
Philess wants to merge 1 commit intogithub:stagedfrom
Philess:staged

Conversation

@Philess
Copy link
Copy Markdown

@Philess Philess commented Apr 24, 2026

Pull Request Checklist

  • I have read and followed the CONTRIBUTING.md guidelines.
  • I have read and followed the Guidance for submissions involving paid services.
  • My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
  • The file follows the required naming convention.
  • The content is clearly structured and follows the example format.
  • I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
  • I have run npm start and verified that README.md is up to date.
  • I am targeting the staged branch for this pull request.

Description

Added a custom agent and a custom instructions files to activate "Caveman" mode which highly reduce token consumption by simplifying to the max the response structure and sentences. (50 to 70%)
Usable as custom agent or with any other type of agent, plan mode and ask mode with the instructions file version


Type of Contribution

  • New instruction file.
  • New prompt file.
  • New agent file.
  • New plugin.
  • New skill file.
  • New agentic workflow.
  • Update to existing instruction, prompt, agent, plugin, skill, or workflow.
  • Other (please specify):

Additional Notes


By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

Copilot AI review requested due to automatic review settings April 24, 2026 11:52
@Philess Philess requested a review from aaronpowell as a code owner April 24, 2026 11:52
@github-actions
Copy link
Copy Markdown
Contributor

🔍 Skill Validator Results

⛔ Findings need attention

Scope Checked
Skills 1
Agents 1
Total 2
Severity Count
--- ---:
❌ Errors 2
⚠️ Warnings 0
ℹ️ Advisories 0

Summary

Level Finding
[agent:Caveman Mode] Agent name 'Caveman Mode' does not match filename 'caveman-mode.agent.md' (expected 'Caveman Mode.agent.md').
[agent:Caveman Mode] Agent name 'Caveman Mode' contains invalid characters — must be lowercase alphanumeric and hyphens only.
Full validator output ```text Found 1 agent(s) ❌ [agent:Caveman Mode] Agent name 'Caveman Mode' does not match filename 'caveman-mode.agent.md' (expected 'Caveman Mode.agent.md'). ❌ [agent:Caveman Mode] Agent name 'Caveman Mode' contains invalid characters — must be lowercase alphanumeric and hyphens only. Validated 1 agent(s)

{Ansi.Red}Agent spec conformance failures — fix the errors above.{Ansi.Reset}

</details>
> **Note:** The validator returned a non-zero exit code. Please review the findings above before merge.

Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a “Caveman Mode” agent and companion custom instructions to encourage terse, low-token responses, and documents them in the repository indexes.

Changes:

  • Added caveman-mode.instructions.md to provide low-token response directives via reusable instructions.
  • Added caveman-mode.agent.md to offer the same behavior as a selectable custom agent.
  • Updated the instructions and agents README indexes to include install links for the new files.
Show a summary per file
File Description
instructions/caveman-mode.instructions.md New instruction file defining terse/low-token response rules (with required front matter).
agents/caveman-mode.agent.md New agent file defining “Caveman Mode” behavior (with required front matter).
docs/README.instructions.md Adds the new instruction entry + install links to the instructions catalog.
docs/README.agents.md Adds the new agent entry + install links to the agents catalog.

Copilot's findings

  • Files reviewed: 4/4 changed files
  • Comments generated: 0

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants