A workflow for combining several dependent GitHub pull requests into one shared starting branch.

Use it to find dependency issues and their open pull requests, verify they are ready, merge them in a fixed order, and update the target issue's dependencies.

It addresses cases where an issue depends on two or more changes and the normal scheduler cannot place them into a single branch stack.

How open-horizon-labs/repo-native-alignment configures Claude Code and

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-join/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/oh-join/github.svg)](https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/oh-join)

Your own site

<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/oh-join"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/oh-join/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/oh-join"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/oh-join.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,341 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.01341
Opus 5	$0.00012	$0.00671
Sonnet 5	$0.00005	$0.00268
Haiku 4.5	$0.00002	$0.00134

Measured 10d ago against content hash 430acee6a11f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

oh-join 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 10d 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-join/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oh-join

Use this skill when an issue has 2+ open dependencies and scheduler cannot auto-stack because there is no single base branch.

Invocation

/oh-join <issue-number>

<issue-number>: target GitHub issue (for example 1178 or #1178)

Goal

For target issue #X:

Read Depends on: dependencies
Find linked open PRs for those dependency issues
Verify dependency PRs are ready to merge
Merge them into one common base branch in deterministic order
Update target issue dependencies to reflect merged deps
Signal completion with outcome details

Flow

Load issue and dependencies
```
gh issue view <issue-number> --json number,title,body,state,url
```
- Parse all dependency numbers from Depends on: lines.
- If fewer than 2 dependencies: stop with blocked (not a join case).
Discover open PRs for dependency issues
```
gh pr list --state open --json number,title,headRefName,baseRefName,body,url
```
- Map dependency issue number -> linked PR by either:
  - branch pattern issue/<N> or issue-<N>
  - PR body containing Closes #N / Fixes #N / Resolves #N
- If any dependency has no open PR: stop with blocked and list missing deps.
Determine common base branch
- Collect baseRefName across dependency PRs.
- If all same: that is the common base branch.
- If different:
  - Attempt to find shared upstream branch by checking whether all base branches descend from a common candidate.
  - If no safe common base is found, stop with blocked and report conflicting bases.
Readiness checks for each dependency PR For each dep PR:
```
gh pr checks <pr-number> --fail-on-error
gh pr view <pr-number> --json reviewDecision,isDraft,mergeable
```
- Must not be draft
- Must be mergeable
- CI checks must pass
- Review decision must not be CHANGES_REQUESTED
- The complete repository /ship pipeline must be evidenced on the final commit
- Every PR must have an explicit APPROVE from a fresh, separate repo-local /review sub-agent for the exact final commit
- Any diff change after that approval invalidates it and requires a new fresh reviewer
- CodeRabbit is optional supplemental feedback: never trigger or wait for it, but verify any actionable comments already present were addressed If any fail: stop with blocked and report specific PR reasons.

Read the full file on GitHub · 155 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.

10d ago First seen · 155 lines · 23 tokens per session scan A 430acee6a11f

Subscribe to this mod's changes

oh-join is a skill published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,341 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.

Git and workflow Project management

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

shiplog

Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.

aeonfun/aeon · 46 tokens

llxprt-issue-workflow

Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…

vybestack/llxprt-code · 87 tokens

repo-native-alignment: Skill for Claude Code