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/mezotv/proofdrop/code-organizationnpx skills add mezotv/proofdrop --skill code-organizationgit clone --depth 1 https://github.com/mezotv/proofdropWhat 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 | $0.00108 | $0.00879 |
| Opus 5 | $0.00054 | $0.00439 |
| Sonnet 5 | $0.00022 | $0.00176 |
| Haiku 4.5 | $0.00011 | $0.00088 |
Grade A, and why
code-organization 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-organization
Where each kind of code goes. Apply this every time you create a file or add a type, schema, helper, or constant. Don't inline them next to feature code and don't pile unrelated things into one file.
Layout
Each category gets its own dedicated folder. Files inside a folder are
grouped by domain (e.g. user, post), not by individual symbol.
src/
types/ type & interface definitions types/user.ts
schemas/ validation schemas (zod, yup, etc.) schemas/user.ts
utils/ helper / utility functions utils/format.ts
constants/ constant values, enums, config constants/routes.ts
Rules
-
One folder per category —
types/,schemas/,utils/,constants/. A new type goes intypes/, never inline in the file that uses it or alongside a component. -
Group files by domain inside a folder. All user-related types live in
types/user.ts; all user-related constants inconstants/user.ts. Split a file once it covers clearly separate domains — not per symbol. -
Functions get their own file. A reusable helper lives in
utils/in a file named for what it does (utils/format.ts,utils/slugify.ts). Keep one focused concern per file; don't accumulate autils/index.tsjunk drawer. -
No barrel files. Do not add
index.tsre-export barrels. Import directly from the specific file:import { formatDate } from "@/utils/format"; // ✓ import { formatDate } from "@/utils"; // ✗ no barrelThis keeps imports explicit and avoids circular-import and tree-shaking surprises.
-
Types vs schemas are separate concerns.
types/holds pure TypeScript type/interface declarations.schemas/holds runtime validation schemas. If a type is derived from a schema, infer it intypes/and import the schema — keep the validator inschemas/.
Where does it go?
| You're adding… | Folder | Example file |
|---|---|---|
type / interface |
types/ |
types/user.ts |
| validation / parse schema | schemas/ |
schemas/user.ts |
| pure helper function | utils/ |
utils/format.ts |
| constant, enum, config literal | constants/ |
constants/routes.ts |
| React component, route, feature code | feature dir | user/profile.tsx |
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 · 78 lines · 108 tokens per session scan A ff8d33a90b7a
code-organization is a skill published in the GitHub repository mezotv/proofdrop (3 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 879 once invoked, about $0.0005 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…