
Git Commits
Intercepts git commit requests and strips out Claude's attribution footprint before committing. Instead of letting Claude run git commit directly (which adds "Generated with Claude Code" and co-author lines), this forces use of a /commit skill that removes that metadata so commits look user-authored. Also generates a reasoning.md file to capture what was tried during the session, which is honestly pretty useful for tracking your build history. Triggers on words like "commit", "push", or "save changes". If you're bothered by AI attribution showing up in your commit history or want cleaner logs, this handles it automatically.
- skills.sh installs
- 523
- GitHub stars
- 3.9K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add parcadei/continuous-claude-v3 --skill git-commits --agent claude-codeInstalls into .claude/skills of the current project.
Files
Git Commit Rules
When the user asks to commit, push, or save changes to git:
MUST Use /commit Skill
DO NOT run git commit directly. Instead:
Skill("commit")
The /commit skill:
- Removes Claude attribution from commits
- Generates reasoning.md capturing what was tried
- Clears build attempts for next feature
Why This Matters
- Regular
git commitadds "Generated with Claude Code" and Co-Author lines - The
/commitskill removes these so commits appear user-authored - Reasoning capture preserves build history for future sessions
Trigger Words
When you see these in user prompts, use the commit skill:
- "commit", "push", "save changes"
- "push to github", "push changes"
- "commit and push"
After Commit
The skill will prompt you to run:
bash "$CLAUDE_PROJECT_DIR/.claude/scripts/generate-reasoning.sh" <hash> "<message>"
Then push if requested:
git push origin <branch>
Sponsors
Details
- Repository
- github.com/parcadei/continuous-claude-v3
- Category
- Git & Pull Requests
- First seen
- Jun 3, 2026
More from parcadei/continuous-claude-v3
All 108- Remember523
- Repo Research Analyst522
- Review521
- Planning Agent520
- Repoprompt517
- Agent Context Isolation514
- Parallel Agents514
- Create Handoff512
- Continuity Ledger511
- Debug509
- Hooks509
- Prove508
- Compound Learnings507
- Hook Developer506
- Tldr Code506
- Commit503
- Research External503
- Test503
- Background Agent Pings502
- Debug Hooks501
- Describe Pr501
- Braintrust Tracing498
- Opc Architecture497
- Shapely Compute497