Skip to content
This repository was archived by the owner on Oct 16, 2026. It is now read-only.
This repository was archived by the owner on Oct 16, 2026. It is now read-only.

docs: evals for engineering plugins #919

Closed
Task
#1091
Closed
docs: evals for engineering plugins#919
Task
#1091

Description

@christso
christso
opened on Apr 2, 2026

Proposal

Add eval where you simply provide the issue.

#912

Compare superpowers and other engineering plugins.

Which one consumers less tokens and completed in less time

Reproduction

Claude Opus 4.6 (200K context)

with baseline

  • TODO

with superpowers:

  • TODO

with hivespec

  • devbox-2: /home/christso/.claude/projects/-home-christso-projects-agentv-allagents/e517648a-b812-42a9-aca8-e10d7418c2e9.jsonl

Activity

  1. christso
    added the
    Task
    issue type on Apr 11, 2026
  2. github-project-automation
    added this to AgentV OSS Boardon Apr 13, 2026
  3. github-project-automation
    moved this to Backlog in AgentV OSS Boardon Apr 13, 2026
  4. christso
    moved this from Backlog to Ready in AgentV OSS Boardon Apr 13, 2026
  5. christso
    changed the title [-]docs: evals for superpowers plugin[/-] [+]docs: evals for engineering plugins[/+] on Apr 13, 2026
  6. christso
    added 2 commits that reference this issue on Apr 13, 2026

    docs(showcase): add multi-plugin benchmark with baseline comparison

    7738a98

    docs(showcase): add multi-plugin benchmark with baseline comparison

    2e17702
  7. christso
    closed this as completedin #1091on Apr 14, 2026
  8. christso
    added a commit that references this issue on Apr 14, 2026

    docs(showcase): add bug-fix-benchmark example for SWE-bench style eva…

    5af7455
  9. christso
    moved this from Ready to In review in AgentV OSS Boardon Apr 15, 2026
  10. christso
    moved this from In review to Done in AgentV OSS Boardon Apr 15, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    Task

    Projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions