companion: Skill for Claude Code

.agents/skills/ship-pr-dev/SKILL.md

ship-pr-dev is a skill for Claude Code from The-Vibe-Company/companion. It costs 134 tokens per session (2,227 once invoked), scanned A, original, MIT.

A delivery workflow that takes a code branch through checks and prepares a pull request (a proposed code change) for human review.

In plain words
What is it for?
Use it to clean up a branch, run verification, make CI pass, and produce a pull request ready for someone to review and merge.
Why use it?
It keeps the steps of checking, committing, pushing, and updating the pull request coordinated while protecting unrelated work and public history.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents); mentions Codex.

This is The-Vibe-Company/companion's own configuration. It tells Claude Code how to work on companion 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 companion configures →

About the project

Companion is a self-hosted, multi-tenant hub for managing personal and organizational SKILL.md libraries used by coding agents. It is for organizations that need to store, validate, version, share, install, update, and synchronize agent skills, with optional named companions that have persistent workspaces and chats. The catalogue skills, agents, and instructions are resources managed or used within this workflow.

The-Vibe-Company/companion · 2,401 stars · on GitHub · thecompanion.sh

Reuse

Borrowing it

Nothing to install: this file belongs to The-Vibe-Company/companion. 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/The-Vibe-Company/companion/main/.agents/skills/ship-pr-dev/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/The-Vibe-Company/companion

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.

agentmods badge for ship-pr-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/the-vibe-company/companion/ship-pr-dev/github.svg)](https://agentmods.dev/skills/the-vibe-company/companion/ship-pr-dev)
Your own site
<a href="https://agentmods.dev/skills/the-vibe-company/companion/ship-pr-dev"><img src="https://agentmods.dev/badge/skills/the-vibe-company/companion/ship-pr-dev/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 ship-pr-dev

Your own site · 80×15
<a href="https://agentmods.dev/skills/the-vibe-company/companion/ship-pr-dev"><img src="https://agentmods.dev/badge/skills/the-vibe-company/companion/ship-pr-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,227 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.02227
Opus 5 $0.00067 $0.01113
Sonnet 5 $0.00027 $0.00445
Haiku 4.5 $0.00013 $0.00223

Measured 9d ago against content hash c967308f5d6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ship-pr-dev 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/collect_ship_context.py, scripts/prepare_ship_run.py, scripts/test_collect_ship_context.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ship-pr-dev/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship PR

Own delivery from the current branch to a PR that is ready for human review. The coordinator keeps scope, architecture, safety decisions, Git state, PR state, and final verification. Delegate only bounded work orders whose saved context is worth more than the dispatch overhead.

Protected Invariants

  1. Never merge, enable auto-merge, force-push, hard-reset, discard user work, or rewrite public history unless the user explicitly requests that exact operation.
  2. Stage only intentional files. Never use broad staging when unrelated changes exist.
  3. The coordinator is the only Git owner. Workers never stage, commit, push, rebase, merge, stash, create/update a PR, or alter CI settings.
  4. Allow at most one write-capable worker at a time. Reviewers and investigators are read-only.
  5. review-code-dev is the single independent review gate. Do not run a separate Ship PR review board or a second full frontend review; pass the required risk and frontend lenses into one review run.
  6. A PR is ready only when local verification is fresh, review-code-dev has no unresolved P0/P1 findings, every visible non-skipped CI item is green on the latest pushed SHA, and the report-only capture-learning-tools pass completed.
  7. Never bypass checks, use --no-verify, weaken validation, or claim success while CI is pending, stale, partially inspected, failed, cancelled, or attached to another SHA.
  8. Never expose secrets. Stop push/PR work, redact values, and give rotation guidance if one is found.
  9. Write artifacts only under ignored plans/ship-pr-dev/runs/<timestamp>-<repo-slug>/.

References

Read only what the current phase needs:

  • references/workflow.md — detailed delivery loop and retry policy.
  • references/agent-routing.md — host-specific worker models, effort, context, budgets, telemetry, and fallbacks.
  • references/readiness-gates.md — hard blocks and required evidence.
  • references/pr-template.md — PR body and final handoff.

Load the installed review-code-dev skill before the review gate and capture-learning-tools only for the final report-only learning pass. Resolve skills by canonical name; never guess an install path.

Read the full file on GitHub · 144 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. 9d ago First seen · 144 lines · 134 tokens per session scan A c967308f5d6c

Subscribe to this mod's changes

ship-pr-dev is a skill published in the GitHub repository The-Vibe-Company/companion (2,401 stars, last pushed 3d ago), licensed MIT. It adds 134 tokens to every session and 2,227 once invoked, about $0.0007 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 2026-09-02.