Skip to content

feat: specific model/harness/version in PR attribution#283

Merged
kieranklaassen merged 5 commits into
mainfrom
feat/specific-attribution-footer
Mar 17, 2026
Merged

feat: specific model/harness/version in PR attribution#283
kieranklaassen merged 5 commits into
mainfrom
feat/specific-attribution-footer

Conversation

@kieranklaassen

@kieranklaassen kieranklaassen commented Mar 17, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • Replace generic "Generated with Claude Code" footer with dynamic attribution
  • LLMs fill in model, context window, thinking level, harness, and plugin version at commit/PR time
  • Subagents explicitly instructed to do the same in multi-agent workflows

Before / After

Before After
🤖 Generated with Claude Code 🤖 Generated with Claude Opus 4.6 (1M context, extended thinking) via Claude Code
Co-Authored-By: Claude Co-Authored-By: Claude Opus 4.6 (1M context, extended thinking)
[![Compound Engineered](...)] [![Compound Engineering v2.40.0](...)]

Substitution table (from the new docs)

Placeholder Value Example
[MODEL] Model name Claude Opus 4.6, GPT-5.4
[CONTEXT] Context window (if known) 200K, 1M
[THINKING] Thinking level (if known) extended thinking
[HARNESS] Tool running you Claude Code, Codex, Gemini CLI
[HARNESS_URL] Link to that tool https://claude.com/claude-code
[VERSION] plugin.jsonversion 2.40.0

Files changed

  • CLAUDE.md — updated commit convention footer + substitution table
  • plugins/compound-engineering/skills/ce-work/SKILL.md — updated commit template, PR badge, checklist, and substitution table

Test plan

  • Next PR created via /ce:work includes specific model, harness, and version in footer
  • Badge renders correctly with version number

Compound Engineering v2.40.0
🤖 Generated with Claude Opus 4.6 (1M context, extended thinking) via Claude Code

kieranklaassen and others added 5 commits March 16, 2026 20:49
…in version

Replace generic "Generated with Claude Code" footer with dynamic attribution
that includes the actual model name, harness tool, and plugin version. LLMs
fill in their own values at commit/PR time. Subagents are explicitly
instructed to do the same.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Separate MODEL into MODEL, CONTEXT, and THINKING placeholders
so each detail is its own table row and easier to read.

Co-Authored-By: Claude Opus 4.6 (1M context, extended thinking) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context, extended thinking) <noreply@anthropic.com>
@kieranklaassen kieranklaassen merged commit fdbd584 into main Mar 17, 2026
1 check passed
This was referenced Mar 18, 2026
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.

1 participant