pull

A workflow for bringing the latest changes from the shared Git repository into the current branch using a merge. A merge combines the histories of two branches and may require resolving conflicts.

In plain words
What is it for?
Use it when the branch is behind the shared main branch, a push is rejected because the remote changed, or merge conflicts need to be resolved.
Why use it?
It helps keep a feature branch up to date while preserving local work and handling conflicts deliberately. It also requires project checks after the merge.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/openai/symphony/pull
Any agent
npx skills add openai/symphony --skill pull
Clone the repo
git clone --depth 1 https://github.com/openai/symphony

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,039 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.01039
Opus 5 $0.00026 $0.00519
Sonnet 5 $0.00010 $0.00208
Haiku 4.5 $0.00005 $0.00104

Measured yesterday against content hash 7aa0ef5cd877, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pull scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

  • pull — 100% identical, 0 lines differ
  • pull — 100% identical, 0 lines differ
  • pull — 95% identical, 6 lines differ
.codex/skills/pull/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 101 lines · 51 tokens per session scan A 7aa0ef5cd877

Subscribe to this mod's changes

pull is a skill published in the GitHub repository openai/symphony (26,941 stars, last pushed 12d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,039 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens