A workflow for taking a GitHub issue from assignment to a completed draft pull request. It requires planning, an isolated branch or worktree, and a draft pull request before implementation begins.

Use it to claim an open GitHub issue, plan the solution, create its branch and draft pull request, implement the change, and run the repository's checks.

It keeps work tied to a clearly understood issue and makes the proposed change visible before code is modified. This reduces work happening on the wrong branch or outside the issue's scope.

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

Your own site

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

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 646 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	$0.00036	$0.00646
Opus 5	$0.00018	$0.00323
Sonnet 5	$0.00007	$0.00129
Haiku 4.5	$0.00004	$0.00065

Measured 10d ago against content hash 8bb0f9be6ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

oh-task 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-task/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oh-task

Work a GitHub issue through the repository's mandatory draft-PR-first workflow.

Invocation

/oh-task <issue-number> [base-branch]

The base defaults to main. Use another branch only for an intentional stacked PR.

Flow

Load AGENTS.md, relevant .oh/ artifacts, and RNA context.
Fetch and validate the open issue. Stop if it is closed, owned by someone else, or lacks enough information to proceed.
Claim the issue with gh issue edit <issue> --add-assignee @me.
Run the repo-local /aim, /problem-space, /problem-statement, and /solution-space phases at the altitude required by the issue. Record the chosen solution.
Create an isolated branch/worktree from the selected base.

Before changing implementation files, push the branch and open a draft PR:

git push -u origin issue/<number>
gh pr create --draft --base <base-branch> --title "<issue-title>" --body "Closes #<number>

## Problem
<problem statement>

## Chosen solution
<solution-space recommendation>"

Execute the chosen solution. Keep all work within the declared issue scope.
Run project checks and the repo-local /review skill. Fix every actionable finding.
Commit focused changes tagged with the relevant [outcome:X] and push them to the draft PR.
Complete any descendant issues created during execution before declaring the implementation complete.
Invoke repo-local /ship <PR-number>. That pipeline alone marks the PR ready, handles CI, verifies delivery, obtains explicit approval of the final diff from a fresh, separate repo-local /review sub-agent, and merges.
Clean up the worktree only after /ship completes or reports a blocker.

Guardrails

Never implement before the draft PR exists.
Never mark the PR ready or merge directly from this skill.
Never substitute a lightweight review for the full RNA /ship pipeline.
Never merge without an explicit APPROVE from a fresh, separate repo-local /review sub-agent on the current final diff. Any later diff change invalidates approval and requires a new fresh reviewer.
Never trigger or wait for CodeRabbit. If actionable CodeRabbit comments already exist, address them like any other external review feedback.
Use AGENTS.md, .oh/, and RNA for context; do not depend on external task-memory tools.
If completion signaling is unavailable, report COMPLETION: status=<status> pr=<url>.

Read the full file on GitHub · 58 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 · 58 lines · 36 tokens per session scan A 8bb0f9be6ffd

Subscribe to this mod's changes

oh-task is a skill published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 646 once invoked, about $0.0002 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