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/composenpx skills add maxtechera/ship --skill composegit 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 | $0.00022 | $0.00578 |
| Opus 5 | $0.00011 | $0.00289 |
| Sonnet 5 | $0.00004 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
content-compose 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Compose
Create a pillar asset (script, post, article) grounded in real evidence.
When to Use
- Starting a new piece with research material available
- Creating the "anchor" piece before waterfall derivatives
- When source material exists but needs shaping into a voice-aligned draft
Inputs Required
- Topic/angle (from ticket or brief)
- Research evidence shortlist (source URLs + key takeaways + VoC pain points)
- Voice samples or exemplars (best-performing past content in the same format)
- Channel and format (reel script / caption / thread / blog)
Process
1. Clarify with Targeted Questions
Before drafting, elicit 5-8 specifics from the owner:
- "What's the one thing the audience should remember?"
- "What proof or receipts do you have that others don't?"
- "What's the controversial or counterintuitive angle here?"
- "What's the exact moment a reader should think 'this is for me'?"
2. Ground in Evidence
For each major claim in the draft:
- Link to a source (research URL, VoC quote, or data point)
- If no evidence exists: mark claim with
[TODO: receipt needed] - Never fabricate specifics
3. Write the Pillar Draft
Apply voice constraints:
- Use real pain language from VoC, not abstract descriptions
- Avoid AI cadence phrases
- Hook structure: Persona + Pain + Outcome + Mechanism + Proof + CTA
- One dominant CTA — not multiple
4. Evidence References
Every draft includes an evidence section:
## Evidence Used
- [Claim] → [Source URL] ([date])
- [Statistic] → [Source URL] ([date])
- [Quote] → [VoC source + date]
Required Outputs
- 5-8 targeted questions (with answers from owner before draft)
- Pillar one-shot draft (format-appropriate)
- Evidence refs linked (source URL per claim)
- Voice check passed (no AI filler, channel format correct)
Failure Policy
- Missing evidence: draft with
[TODO: receipt needed]markers, request the missing items - Missing voice samples: draft conservatively, flag for review
- Ambiguous angle: ask before drafting, not after
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 · 79 lines · 22 tokens per session scan A 00978cc63fcf
content-compose is a skill published in the GitHub repository maxtechera/ship (2 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 578 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…