ship-loop

ship-loop is a skill for Claude Code, Codex, Cursor from ashishpatill/tell-proof. It costs 55 tokens per session (623 once invoked), scanned A, original, MIT.

Instructions for taking a pull request from review to merge: inspect it, fix blocking issues, commit the changes, push them, and merge once local checks pass.

In plain words
What is it for?
Use it when asked to ship, merge, or run a ship-loop on a pull request, including checking tests, addressing review issues, and iterating on the branch.
Why use it?
It gives an agent a repeatable process for handling unfinished pull requests instead of stopping after making a partial fix.

Skill for Claude CodeCodexCursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ashishpatill/tell-proof/ship-loop
Any agent
npx skills add ashishpatill/tell-proof --skill ship-loop
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: Claude Code, Codex, Cursor.

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-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashishpatill/tell-proof/ship-loop.svg)](https://agentmods.dev/skills/ashishpatill/tell-proof/ship-loop)
Your own site
<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/ship-loop"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/ship-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 623 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00055 $0.00623
Opus 5 $0.00028 $0.00311
Sonnet 5 $0.00011 $0.00125
Haiku 4.5 $0.00006 $0.00062

Measured 4d ago against content hash 18d7a723c407, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship-loop 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 4d 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.

.cursor/skills/ship-loop/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship loop

Close the loop from “open PR” to “merged on the base branch.” No vibes. No attribution noise.

Invariants

  1. Semantic commits onlyfeat|fix|docs|test|chore|refactor(scope): summary. One concern per commit.
  2. No attribution — do not add Co-authored-by, Signed-off-by, or names of tools/agents/people in commit subjects or bodies.
  3. Push every cyclegit push -u origin <branch> after each commit batch.
  4. Do not force-push to a shared PR branch unless the user explicitly asks.
  5. Merge only when greenlocal gates pass (pnpm test / typecheck / package tests). Never wait on or re-run GitHub Actions; remote CI is out of scope unless the user explicitly asks about it.
  6. Prefer the PR that contains the work just shipped — if multiple drafts stack, merge the tip that includes the rest (or merge base then tip in order).

Loop

Step Action
1. Identify gh pr view <n> / gh pr checks <n> — branch, base, checks, review threads
2. Diagnose Local typecheck/tests, Playwright eye for UI PRs, leftover draft status — not GitHub Actions
3. Fix Smallest change that clears a named local failure
4. Commit Semantic message, no attribution trailers
5. Push Upstream the branch
6. Re-check Re-run local gates; if red, go to 2
7. Ready Undraft if still draft
8. Merge Only if user asked (merge / merge when ready). Prefer local green over remote CI.

Local gates (Tell)

pnpm -F @tell/design-skills test   # if engine touched
pnpm -F @tell/web typecheck
pnpm test                          # if broader

For showcase/UI: Playwright eye on /showcase — craft beat visible, no empty right gutter, no nav-only thumbs.

Stop conditions

  • Done: PR merged, branch deleted optional, working tree clean vs base.
  • Blocked: Missing permissions, failing required check you cannot fix, or user-required review — report the blocker; do not fake a merge.

Read the full file on GitHub · 54 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. 4d ago First seen · 54 lines · 55 tokens per session scan A 18d7a723c407

Subscribe to this mod's changes

ship-loop is a skill published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 9d ago), licensed MIT. It adds 55 tokens to every session and 623 once invoked, about $0.0003 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

animate-text

Curated text animation catalog with exact JSON specs for headings, labels, counters, and text swaps. Use when an agent needs to pick or translate named effects like soft blur in, typewriter, shared axis, line reveal, stagger, crossfade, or kinetic builds into WAAPI, Motion, Framer Motion, GSAP, CSS, Lottie, Rive, or…

marvkr/better-design · 81 tokens

better-design

Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…

marvkr/better-design · 77 tokens

vfx-text-cursor

Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.

nexu-io/open-design · 28 tokens

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens