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/lukedj78/dev-flow/composition-patterns-guidenpx skills add lukedj78/dev-flow --skill composition-patterns-guidegit clone --depth 1 https://github.com/lukedj78/dev-flowWhat 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 | $0.00185 | $0.02435 |
| Opus 5 | $0.00093 | $0.01218 |
| Sonnet 5 | $0.00037 | $0.00487 |
| Haiku 4.5 | $0.00018 | $0.00244 |
Grade A, and why
composition-patterns-guide 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 2d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
composition-patterns-guide — modern React composition + our colocation rules
This skill is a knowledge guardrail that activates whenever you're designing, refactoring, or reviewing the architecture of a React/RN component. It combines two layers:
- The 7 Vercel
composition-patternsrules (originally fromvercel-labs/agent-skills), adapted to our stack. - Our colocation rules (Rule of Three for promotion, L0/L1/L2,
_components/andcomponents/shared/<dominio>/).
It does NOT execute refactors — for that, use promote-component. It provides the thinking framework.
When this skill applies
- About to add a 4th boolean prop to an existing component.
- About to write a component with
renderHeader,renderFooter,renderActionsrender-prop callbacks. - A component grew over ~250 lines and needs structural refactor.
- You see prop drilling 3+ levels deep.
- About to use
forwardRefin new code (React 19+ projects). - Reviewing a PR that touches component architecture.
Orchestrator does NOT route here automatically — invoked by the agent's own judgment when the patterns match.
The 7 composition rules (priority order)
Priority 1 — Component Architecture (HIGH)
Rule 1: Avoid boolean prop proliferation
Wrong:
<Composer
onSubmit={...}
isThread={true}
channelId={42}
isDMThread={false}
dmId={null}
isEditing={true}
isForwarding={false}
/>
Each boolean doubles the state-space. 5 booleans = 32 possible combinations, most of which are invalid or untested.
Right (composition):
<Composer>
<Composer.Header />
<Composer.Input />
<Composer.ThreadField channelId={42} />
<Composer.EditActions />
<Composer.Footer onSubmit={...} />
</Composer>
The consumer composes the parts they need. No invalid states.
Rule 2: Use compound components
A complex component should expose subcomponents that share context, not a single API with N props.
Wrong:
function Card({ title, body, footer, showAvatar, avatarUrl }) {
return <div>...</div>;
}
What ships with it
3 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.
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.
- 2d ago First seen · 227 lines · 185 tokens per session scan A d34801101aff
composition-patterns-guide is a skill published in the GitHub repository lukedj78/dev-flow (5 stars, last pushed 4d ago), licensed MIT. It adds 185 tokens to every session and 2,435 once invoked, about $0.0009 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
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
evaluating-code-models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步(architecture-sync)。OpenCode / Claude / Codex / Cursor 通用。.