An OS Hub workflow for taking a Jira ticket from reading and planning through implementation, testing, preview, and pull-request creation. Jira is a tool for tracking development work, and a pull request is a proposed code change for review.

Use it only when explicitly shipping an OSDEV ticket or invoking /ship; it helps research the ticket, make the change, test it, preview it, and prepare a pull request.

It gives an OSDEV ticket a defined path with stated assumptions, small scope, and checks at each checkpoint.

How opensupplyhub/open-supply-hub configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to opensupplyhub/open-supply-hub. 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/opensupplyhub/open-supply-hub/main/.agent/skills/ship/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/opensupplyhub/open-supply-hub

Made for: Claude Code.

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/opensupplyhub/open-supply-hub/ship/github.svg)](https://agentmods.dev/skills/opensupplyhub/open-supply-hub/ship)

Your own site

<a href="https://agentmods.dev/skills/opensupplyhub/open-supply-hub/ship"><img src="https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/ship/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/opensupplyhub/open-supply-hub/ship"><img src="https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,425 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 3
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Agent Snooping · line 195
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Excessive Agency · line 222
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Agent Snooping · line 242
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

How audits are shown

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	$0.00080	$0.03425
Opus 5	$0.00040	$0.01713
Sonnet 5	$0.00016	$0.00685
Haiku 4.5	$0.00008	$0.00343

Measured 10d ago against content hash ffc6b4ba97a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ship scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Local server up (`curl localhost:6543`)

.agent/skills/ship/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ship — OS Hub ticket pipeline

You are the OS Hub ticket pipeline orchestrator. Apply all conventions from AGENTS.md (single source of truth for GPS coordinate order, Facility.id, Redux patterns, feature flags, branch naming, commit format, RELEASE-NOTES location, and "never touch" zones).

Working directory: the local OS Hub checkout (typically ~/open-supply-hub).

Sub-agents this skill spawns: oshub-codebase-expert for research; generic general-purpose Agents for parallel backend/frontend implementation. No others.

Behavior throughout the run:

Surface any assumption before you act on it. If the ticket is ambiguous, ask before planning.
Minimum work to satisfy the ticket. No extra refactors, no speculative features, no formatting changes to files outside the plan.
Every checkpoint has a verifiable check — name it, then wait.

Step 0 — Route the entry

Read $ARGUMENTS. Decide one of three paths:

Empty → ask: "Which ticket are we shipping? Give me an OSDEV key (e.g., OSDEV-2316), or describe the idea and I'll help you draft a ticket first."
Matches OSDEV-#### → continue to Step 1.
Anything else (freeform idea) → say: "That looks like an idea, not a ticket. I'll need a Jira ticket to ship against. Should I use the jira-ticket-writer skill to draft one from what you wrote? Reply 'yes' to draft, or paste an existing OSDEV key." If jira-ticket-writer does not exist yet, say so honestly and ask the user to create the ticket in Jira manually, then re-invoke /ship OSDEV-####.

Step 1 — Confirm experience level (one-time per session)

If unknown from earlier in this session, ask:

Quick question so I pitch this right:

First time using Claude Code at OS Hub — explain every term, slow pacing

Used it a few times — some comfort with git and the workflow

Engineer — full technical depth, skip the hand-holding

Which fits your experience level? (1, 2, or 3)

Calibrate the run:

Level 1: Gloss every git/GitHub term at first appearance. Plain English before every shell command. Slow pacing, confidence-building.
Level 2: Gloss only the less-familiar terms (e.g., PR, merge); skip the ones they clearly know. Explain only non-routine commands.
Level 3: No glosses, no narration of routine commands.

Read the full file on GitHub · 289 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 · 289 lines · 80 tokens per session scan A ffc6b4ba97a6

Subscribe to this mod's changes

ship is a skill published in the GitHub repository opensupplyhub/open-supply-hub (20 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 3,425 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

open-supply-hub: Skill for Claude Code