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/moasq/agentic-ship/convex-structurenpx skills add moasq/agentic-ship --skill convex-structuregit clone --depth 1 https://github.com/moasq/agentic-shipWrote 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.
[](https://agentmods.dev/skills/moasq/agentic-ship/convex-structure)<a href="https://agentmods.dev/skills/moasq/agentic-ship/convex-structure"><img src="https://agentmods.dev/badge/skills/moasq/agentic-ship/convex-structure.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.02790 |
| Opus 5 | $0.00026 | $0.01395 |
| Sonnet 5 | $0.00010 | $0.00558 |
| Haiku 4.5 | $0.00005 | $0.00279 |
Grade A, and why
convex-structure 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.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convex Structure
Downstream contract: paths like
src/andconvex/refer to the product workspace that adopts Agentic Ship, not this tool repo.
Official Convex skills (from the convex plugin) teach Convex. This skill teaches
Convex inside this repo — the conventions that let an agent open a cold codebase and
know exactly where everything goes without reading it all first.
Every rule here is deterministic. If you find yourself deciding, you have missed a rule.
1. File layout — one domain per file
convex/
schema.ts every table, every index. Nothing exists unless declared here.
convex.config.ts component registration (Better Auth, and later others)
auth.config.ts auth provider declaration
auth.ts createAuth + authComponent. Plugins toggle here.
http.ts httpRouter: auth routes + inbound webhooks. Nothing else.
<domain>.ts (you create) the entire public API of one domain, e.g. posts.ts
lib/
auth.ts requireUser / requireOwner helpers
validators.ts (you create) shared validator fragments, once two domains share one
_generated/ created by `npx convex dev`; committed then, never edited by hand
Rules:
- A domain gets its own file the moment it owns a table.
users.ts,posts.ts,waitlist.ts. Never autils.tsdumping ground, never afunctions.ts. - Domain names are plural nouns matching the table name. Table
posts→ fileconvex/posts.ts→ frontend feature foldersrc/components/features/posts/. One word, three places, no translation needed. - Cross-domain reads go through the owning domain's file. If
posts.tsneeds a user, it calls a helper fromlib/auth.ts— it does not query the users table directly. One writer per table.
2. Function shape — the only accepted template
Every function, without exception:
export const create = mutation({
args: { title: v.string() }, // ALWAYS present
returns: v.id("posts"), // ALWAYS present
handler: async (ctx, args) => {
const user = await requireUser(ctx); // identity from ctx, never from args
return await ctx.db.insert("posts", { title: args.title, userId: user._id });
},
});
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/better-auth-hardening.md 5.0 KB
- references/better-auth-wiring.md 10 KB
- references/deploy-netlify.md 7.3 KB
- references/deploy-vercel.md 2.9 KB
- references/deployment-cloudflare.md 8.1 KB
- references/email-resend.md 3.3 KB
- references/example-domain.md 7.5 KB
- references/lemon-squeezy-billing.md 5.8 KB
- references/polar-billing.md 4.4 KB
- references/stripe-billing.md 9.2 KB
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.
- 4d ago First seen · 238 lines · 52 tokens per session scan A eb3d0361175e
convex-structure is a skill published in the GitHub repository moasq/agentic-ship (11 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 2,790 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…