MCPInstall

pull

Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution best practices.

Installs
541
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/odysseus0/symphony --skill pull
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads pull automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Pull

Workflow

  1. Verify git status is clean or commit/stash changes before merging.
  2. Ensure rerere is enabled locally:
    • git config rerere.enabled true
    • git config rerere.autoupdate true
  3. Confirm remotes and branches:
    • Ensure the origin remote exists.
    • Ensure the current branch is the one to receive the merge.
  4. Fetch latest refs:
    • git fetch origin
  5. Sync the remote feature branch first:
    • git pull --ff-only origin $(git branch --show-current)
    • This pulls branch updates made remotely (for example, a GitHub auto-commit) before merging origin/main.
  6. Merge in order:
    • Prefer git -c merge.conflictstyle=zdiff3 merge origin/main for clearer conflict context.
  7. If conflicts appear, resolve them (see conflict guidance below), then:
    • git add <files>
    • git commit (or git merge --continue if the merge is paused)
  8. Verify with project checks (follow repo policy in AGENTS.md).
  9. Summarize the merge:
    • Call out the most challenging conflicts/files and how they were resolved.
    • Note any assumptions or follow-ups.

Conflict Resolution Guidance (Best Practices)

  • Inspect context before editing:
    • Use git status to list conflicted files.
    • Use git diff or git diff --merge to see conflict hunks.
    • Use git diff :1:path/to/file :2:path/to/file and git diff :1:path/to/file :3:path/to/file to compare base vs ours/theirs for a file-level view of intent.
    • With merge.conflictstyle=zdiff3, conflict markers include:
      • <<<<<<< ours, ||||||| base, ======= split, >>>>>>> theirs.
      • Matching lines near the start/end are trimmed out of the conflict region, so focus on the differing core.
    • Summarize the intent of both changes, decide the semantically correct outcome, then edit:
      • State what each side is trying to achieve (bug fix, refactor, rename, behavior change).
      • Identify the shared goal, if any, and whether one side supersedes the other.
      • Decide the final behavior first; only then craft the code to match that decision.
      • Prefer preserving invariants, API contracts, and user-visible behavior unless the conflict clearly indicates a deliberate change.
    • Open files and understand intent on both sides before choosing a resolution.
  • Prefer minimal, intention-preserving edits:
    • Keep behavior consistent with the branch’s purpose.
    • Avoid accidental deletions or silent behavior changes.
  • Resolve one file at a time and rerun tests after each logical batch.
  • Use ours/theirs only when you are certain one side should win entirely.
  • For complex conflicts, search for related files or definitions to align with the rest of the codebase.
  • For generated files, resolve non-generated conflicts first, then regenerate:
    • Prefer resolving source files and handwritten logic before touching generated artifacts.
    • Run the CLI/tooling command that produced the generated file to recreate it cleanly, then stage the regenerated output.
  • For import conflicts where intent is unclear, accept both sides first:
    • Keep all candidate imports temporarily, finish the merge, then run lint/type checks to remove unused or incorrect imports safely.
  • After resolving, ensure no conflict markers remain:
    • git diff --check
  • When unsure, note assumptions and ask for confirmation before finalizing the merge.

When To Ask The User (Keep To A Minimum)

Do not ask for input unless there is no safe, reversible alternative. Prefer making a best-effort decision, documenting the rationale, and proceeding.

Ask the user only when:

  • The correct resolution depends on product intent or behavior not inferable from code, tests, or nearby documentation.
  • The conflict crosses a user-visible contract, API surface, or migration where choosing incorrectly could break external consumers.
  • A conflict requires selecting between two mutually exclusive designs with equivalent technical merit and no clear local signal.
  • The merge introduces data loss, schema changes, or irreversible side effects without an obvious safe default.
  • The branch is not the intended target, or the remote/branch names do not exist and cannot be determined locally.

Otherwise, proceed with the merge, explain the decision briefly in notes, and leave a clear, reviewable commit history.

FAQ

What does the pull skill do?

Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution best practices.

How do I install pull?

Run npx skills add https://github.com/odysseus0/symphony --skill pull in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/pull/ (personal) or .claude/skills/pull/ (project).

Which AI agents can use pull?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is pull safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains pull?

It is published by odysseus0 in odysseus0/symphony. It has 541 recorded installs.

More from odysseus0/symphony

View all →

debug

odysseus0/symphony

Investigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.

land

odysseus0/symphony

Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.

linear

odysseus0/symphony

Linear GraphQL patterns for Symphony agents. Use lineargraphql for all operations — comments, state transitions, PR attachments, file uploads, and issue creation. Never use schema introspection.

push

odysseus0/symphony

Push current branch changes to origin and create or update the corresponding pull request; use when asked to push, publish updates, or create pull request.

commit

odysseus0/symphony

Create a well-formed git commit from current changes using session history for rationale and summary; use when asked to commit, prepare a commit message, or finalize staged work.

symphony-setup

odysseus0/symphony

Open the skill to read its SKILL.md instructions.

261 installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.