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 skills add punkadillo/figma-code-composer --skill feature-archgit clone --depth 1 https://github.com/punkadillo/figma-code-composerWrote 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/punkadillo/figma-code-composer/feature-arch)<a href="https://agentmods.dev/skills/punkadillo/figma-code-composer/feature-arch"><img src="https://agentmods.dev/badge/skills/punkadillo/figma-code-composer/feature-arch.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 5.1 | $0.00108 | $0.01828 |
| Opus 5 | $0.00054 | $0.00914 |
| Sonnet 5 | $0.00022 | $0.00366 |
| Haiku 4.5 | $0.00011 | $0.00183 |
Grade A, and why
feature-arch 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.
This is a copy
95% identical to feature-arch — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature-Based Architecture Best Practices
Comprehensive architecture guide for organizing React applications by features, enabling scalable development with independent teams. Contains 42 rules across 8 categories, prioritized by impact from critical (directory structure, imports) to incremental (naming conventions). When invoked on a real project, the skill produces a project-specific blueprint that anchors every decision in those rules.
Primary Output: The Target Architecture Blueprint
When an agent invokes this skill on a real project, the deliverable is a single
markdown file persisted at docs/architecture/FEATURE-ARCH-TARGET.md (or the
repo's existing docs location). The blueprint contains:
- Project context — framework, state libraries, routing model, current shape.
- Identified features — confirmed with the user, sourced from routes, docs, openspec, and code clusters.
- Target directory tree — literal paths, not pseudo-trees.
- Per-feature public APIs — exact named exports of each
index.ts. - Import-boundary matrix — N×N table of feature relationships (
allowed/forbidden/via app/via events). - State & data ownership — server-state and client-state owner per feature.
- Cross-feature communication policy — composition, events, or shared slice — with rationale.
- Numbered migration plan — file-level move/create/delete steps with S/M/L effort estimates.
- Human conformance checklist — for code review and "definition of done".
- Open questions — anything that needs a human decision before migration.
Every section cites the specific rules below that govern its decisions, so the blueprint stays a projection of this skill — not a parallel authority.
How the agent generates the blueprint
Follow the process in references/_blueprint-process.md. Summary:
- Gather context (package.json, src/ tree, README, CLAUDE.md, openspec/).
- Identify candidate features from routes, docs, and code clusters.
- Confirm the feature list with the user via
AskUserQuestion. - Record explicit decisions (layer model, comm mechanism, state/routing owner).
- Fill in assets/templates/feature-arch-target.md.template — every
{{placeholder}}replaced with a literal project value. - Hand off: print path, summarise feature/step counts, list top-3 risks, suggest next action. Do not start executing migration steps in the same turn.
What ships with it
48 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.
- AGENTS.md 9.3 KB
- assets/templates/_template.md 697 B
- assets/templates/feature-arch-target.md.template 12 KB
- README.md 3.6 KB
- references/_blueprint-process.md 9.8 KB
- references/_sections.md 1.5 KB
- references/bound-event-based-communication.md 2.6 KB
- references/bound-feature-isolation.md 2.3 KB
- references/bound-feature-scoped-routing.md 2.3 KB
- references/bound-feature-size.md 2.3 KB
- references/bound-interface-contracts.md 2.1 KB
- references/bound-minimize-shared-state.md 2.2 KB
- references/fcomp-colocate-styles.md 2.2 KB
- references/fcomp-composition-over-props.md 2.4 KB
- references/fcomp-container-presentational.md 2.5 KB
- references/fcomp-error-boundaries.md 2.5 KB
- references/fcomp-props-as-data-boundary.md 2.5 KB
- references/fcomp-single-responsibility.md 2.6 KB
- references/fquery-avoid-n-plus-one.md 2.3 KB
- references/fquery-colocate-with-feature.md 2.0 KB
- references/fquery-feature-scoped-keys.md 2.1 KB
- references/fquery-parallel-fetching.md 2.2 KB
- references/fquery-server-component-fetching.md 2.3 KB
- references/fquery-single-responsibility.md 2.0 KB
- references/fstate-context-sparingly.md 2.1 KB
- references/fstate-feature-scoped-stores.md 2.2 KB
- references/fstate-lift-minimally.md 2.3 KB
- references/fstate-reset-on-unmount.md 2.3 KB
- references/fstate-server-state-separation.md 2.6 KB
- references/import-avoid-barrel-files.md 2.0 KB
- references/import-no-cross-feature.md 2.4 KB
- references/import-path-aliases.md 1.8 KB
- references/import-public-api.md 2.0 KB
- references/import-type-only.md 2.1 KB
- references/import-unidirectional-flow.md 2.2 KB
- references/name-descriptive-exports.md 2.0 KB
- references/name-feature-naming.md 1.9 KB
- references/name-file-conventions.md 2.3 KB
- references/struct-app-layer.md 2.0 KB
- references/struct-feature-folders.md 2.0 KB
- references/struct-feature-self-contained.md 1.8 KB
- references/struct-flat-hierarchy.md 1.6 KB
- references/struct-optional-segments.md 1.9 KB
- references/struct-shared-layer.md 2.0 KB
- references/test-colocate-with-feature.md 2.0 KB
- references/test-feature-isolation.md 2.2 KB
- references/test-integration-at-app-layer.md 2.7 KB
- references/test-shared-utilities.md 2.5 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 · 156 lines · 108 tokens per session scan A 4e5244d52199
feature-arch is a skill published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 19d ago), licensed MIT. It adds 108 tokens to every session and 1,828 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to feature-arch, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
agent-spec-mobile-react-native
Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.
formkit
Use when working with FormKit forms, validation, schema, or custom inputs in React, Vue, or Nuxt projects.
figma-codegen
Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…
rn-best-practices
This skill should be used when writing or reviewing React Native / Expo code — before writing list rendering, animations, data fetching, component APIs, navigation, or image/media UI — and when asked to "review best practices", "check performance", "optimize renders", "review list rendering", "check animation…