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.
npx agentmods add skills/maxtechera/ship/copynpx skills add maxtechera/ship --skill copygit clone --depth 1 https://github.com/maxtechera/shipWhat 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 | $0.00025 | $0.00575 |
| Opus 5 | $0.00013 | $0.00287 |
| Sonnet 5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
content-copy 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 yesterday.
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.
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.
Content Copy
Generate copy that sounds like a human founder, adapted per platform. All copy goes through a voice system — never write and ship raw AI output.
Process
1. Clarify the Brief
Before writing, establish:
- Topic — core message or claim
- Format — platform/format (reel script, caption, thread, LinkedIn, email, blog)
- Source material — research, transcript, or existing content to repurpose
- CTA goal — what the audience should do (comment, subscribe, click, buy)
2. Ground in Evidence
Pull from available research:
- Audience pain language (VoC bank)
- Proven hook formulas for the format
- Competing content and what's performing
3. Write Using Voice Constraints
Hook structure (persona-led): Persona + Pain + Outcome + Mechanism + Proof + CTA
Voice rules:
- Use real language from pain research, not abstract claims
- Avoid AI-cadence phrases: "delve", "unlock the power of", "comprehensive solution", "game-changer"
- Match platform register (casual for reels, professional for LinkedIn, conversational for email)
- One dominant CTA per piece — never split attention
4. Humanize Pass
Final pass: remove AI patterns, punch up the hook, verify platform formatting.
Platform Formats
| Platform | Format rules |
|---|---|
| Instagram Reel | Hook (0-3s), problem (3-10s), solution (10-45s), CTA (last 3s). Max 150-word caption. |
| Instagram Carousel | Slide 1 = hook/promise. Slides 2-8 = one point each. Last slide = CTA. |
| Twitter/X Thread | Tweet 1 = bold hook claim. Tweets 2-8 = proof/steps. Last tweet = CTA + restate hook. |
| Professional angle, metrics-led, longer form acceptable. Story → lesson → CTA. | |
| Email/Newsletter | Subject line ≤50 chars. Hook in first sentence. Plain text preferred. One CTA. |
| Blog | SEO-structured H2/H3. Intro hooks with pain. One internal link per 500 words. |
Required Outputs
- Full copy draft (format-appropriate)
- Hook variants (2-3 alternates for testing)
- CTA variants (3) by temperature: cold / warm / hot
- Platform-specific formatting applied
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.
- yesterday First seen · 58 lines · 25 tokens per session scan A e45aa579df82
content-copy is a skill published in the GitHub repository maxtechera/ship (2 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 575 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…