repo-native-alignment: Skill for Claude Code

.agents/skills/oh-merge/SKILL.md

oh-merge is a skill for Claude Code, Codex from open-horizon-labs/repo-native-alignment. It costs 18 tokens per session (2,664 once invoked), scanned A, original, MIT.

A workflow for reviewing and merging related GitHub pull requests, which are proposed code changes, as one coordinated batch.

In plain words
What is it for?
Use it to inspect pull requests marked for merging, identify stacked or related branches, resolve conflicts, and squash-merge eligible changes.
Why use it?
It helps handle dependent changes in the right order and includes pull requests with merge conflicts instead of leaving them unresolved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is open-horizon-labs/repo-native-alignment's own configuration. It tells Claude Code and Codex how to work on repo-native-alignment itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything repo-native-alignment configures →

Reuse

Borrowing it

Nothing to install: this file belongs to open-horizon-labs/repo-native-alignment. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/open-horizon-labs/repo-native-alignment/main/.agents/skills/oh-merge/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignment

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for oh-merge

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/oh-merge/github.svg)](https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/oh-merge)
Your own site
<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/oh-merge"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/oh-merge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for oh-merge

Your own site · 80×15
<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/oh-merge"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/oh-merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.02664
Opus 5 $0.00009 $0.01332
Sonnet 5 $0.00004 $0.00533
Haiku 4.5 $0.00002 $0.00266

Measured 12d ago against content hash 7f0059aa1bd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

oh-merge 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 12d ago.

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.

.agents/skills/oh-merge/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oh-merge

Holistically review pending GitHub issue PRs from oh-task, then squash-merge them as a cohesive batch.

Invocation

/oh-merge

Flow

  1. Load project background from AGENTS.md, relevant .oh/ artifacts, and RNA MCP context when available.

  2. Find all PRs with oh-merge label:

    gh pr list --label oh-merge --json number,title,headRefName,baseRefName,additions,deletions
    

    Only PRs with the oh-merge label are eligible for merge.

    IMPORTANT: PRs with merge conflicts ARE eligible. The skill rebases and resolves conflicts in step 6. Do NOT skip PRs because of conflict status - that's exactly what this skill handles.

  3. Build dependency graph and identify stacks:

    • Create adjacency list: baseRefName → [PRs targeting it]

    • Find root PRs: those where baseRefName = main (or master)

    • Identify stacks: chains where child PRs target parent PR branches

    • Detect cycles: If a branch eventually targets itself, report error and skip

    • Example graph:

      main ← PR #42 (issue/123) ← PR #43 (issue/456)
      main ← PR #44 (issue/789)  [separate stack]
      
  4. Select stack to process:

    • If multiple independent stacks exist, pick first by lowest root PR number (FIFO by age)
    • If multiple PRs target the same base branch, order by PR number (lowest first)
    • Report other stacks as "queued for next run"
    • Process only one stack per invocation to keep merges atomic
    • Orphaned children: If a child PR targets a branch that doesn't exist (parent merged externally), update its base to main and treat as a root
  5. Batch review - evaluate all PRs in the selected stack together:

    • Collect combined diff of all PRs against main
    • Run the repo-local /review skill on the combined changes
    • Evaluate:
      • Do changes conflict logically? (same code modified differently)
      • Is there duplicate work? (two PRs solving same problem)
      • Do changes compose well? (feature A + feature B = coherent whole)
      • Any cross-cutting concerns? (shared dependencies, API changes)
    • If concerns found:
      • Report issues
      • Ask human whether to proceed or address first

Read the full file on GitHub · 290 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. 12d ago First seen · 290 lines · 18 tokens per session scan A 7f0059aa1bd7

Subscribe to this mod's changes

oh-merge is a skill published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 2,664 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

oss-maintainer

Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.

debpalash/VoiceStudio · 55 tokens