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/supervisornpx skills add maxtechera/ship --skill supervisorgit 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 | $0.00033 | $0.00677 |
| Opus 5 | $0.00016 | $0.00338 |
| Sonnet 5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
content-engine-supervisor 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Engine Supervisor (Always-On)
Content Engine is skills-first. This supervisor runs bounded one-cycle wakes and exits. It does not stay alive between cycles.
Inputs
- Active ship-engine runs (Linear tickets tagged with run stage)
- Research intel shortlist (ranked by recency + relevance + ROI)
- Semantic inspiration (voice samples, best performers, proven offers)
- Calendar state (current queue status)
- Analytics evidence (for live assets: day-1 and week-1 data)
Core Loop (One Cycle)
1. For each active run → fetch strategy/ICP context (blackboard + stage ticket artifacts)
- Require intake preflight before creating downstream artifacts:
intake.product_brief, intake.interview, intake.research_kickoff
2. Pull ranked research shortlist
- ROI gate: only research with strong engagement signal
- Dedup: skip topics already in queue or recently published
- Recency: prefer fresh evidence (< 30 days)
3. Write context keys:
- awareness.content_candidates
- validate.research_dataset (if applicable)
4. If awareness content is missing for active run → delegate:
- content-compose → pillar draft
- content-waterfall → platform bundle
5. Auto-schedule derivatives
- Drafts only — no publishing
- Respect locked items in the calendar
- Fill gaps, don't overwrite confirmed posts
6. Sync artifacts to Linear and run state:
- outputs.content_calendar
- outputs.content_waterfall
- awareness.content_calendar (blackboard key)
- awareness.content_waterfall (blackboard key)
7. If live permalinks exist → delegate measurement:
- content-measure → measure.kpis + measure.feedback_events
8. Apply learning gate:
- Always log observations
- Update pattern files only when N≥3 data points exist for the pattern
- Update skill defaults only with explicit confirmation
Guardrails
- Draft scheduling is allowed; auto-publishing is not — the owner publishes
- Never fabricate research evidence or metrics
- Never mark deliverables
verifiedorlivewithout a real permalink - Intake preflight is mandatory before creating awareness content for a run
- One cycle = one wake → do work → exit (no persistent loop)
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 · 84 lines · 33 tokens per session scan A 32cd01678a24
content-engine-supervisor is a skill published in the GitHub repository maxtechera/ship (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 677 once invoked, about $0.0002 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…