agentleFS
Sign inStart free
zoranmarticzoranmartic/coord-wright/skills/merge-to-main/SKILL.md

merge-to-main

Skill0 starsChanged 47 days agoApache-2.0View on GitHub

Fast-forward a registered coord session worktree branch into its canonical main checkout. Use when the user says $merge-to-main, \"merge this task branch to main\", or \"promote this worktree branch\".

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run from the session worktree (not the main checkout).

    line 7
  2. Very specific:

    If any match is a real credential, wallet, private key, or DSN: stop, fix on the task branch, push the fix, then re-run without …

    line 26
  3. Very specific:

    Only run from a registered session worktree (<project>-session-*), never from main.

    line 39
  4. Distinctive:

    Never push main until exit 0.

    line 40
  5. Distinctive:

    Never print secret values in the chat response or terminal summary.

    line 41
  6. Distinctive:

    Do not delete or rename the task branch.

    line 42
  7. Distinctive:

    After a successful merge the session worktree remains on its branch, untouched.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Fast-forward the current session worktree branch into canonical main. Run from the session worktree (not the main checkout).

Run

"${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/merge-to-main.sh"

Exit codes

Exit 0 — merge and push complete. Report the output line to the user.

Exit 1 — security finding. The script printed matches from the candidate diff. Evaluate each match against the placeholder allowlist: your-password, <password>, example, changeme, REPLACE_ME, xxx, ***, empty values, ${ENV_VAR}, environment lookups. If all matches are safe:

SKIP_SECURITY=1 "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/merge-to-main.sh"

If any match is a real credential, wallet, private key, or DSN: stop, fix on the task branch, push the fix, then re-run without SKIP_SECURITY=1.

Exit 2 — preflight failure (dirty tree, wrong worktree, branch out of sync, push failed). Report the error message and stop.

Source of truth

  • ${COORD_TOOLS}/docs/coordination.md
  • ${COORD_TOOLS}/projects.txt

Rules

  • Only run from a registered session worktree (<project>-session-*), never from main.
  • Never push main until exit 0.
  • Never print secret values in the chat response or terminal summary.
  • Do not delete or rename the task branch.
  • After a successful merge the session worktree remains on its branch, untouched.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free