project-legibility
v0.17.1by perhapsspy
Keep projects understandable, reviewable, and changeable as agent work accumulates.
What project-legibility does, in the publisher's words
에이전트의 속도에서도 계속 고칠 수 있는 프로젝트.
Project Legibility는 Codex와 Claude Code가 코드를 바꾸는 동안 프로젝트의 구조, 판단 기준과 작업 맥락도 함께 단단하게 만들도록 돕는 스킬 플러그인입니다.
- 코드: 변경이 쌓여도 주 흐름과 책임이 읽히고 계속 고칠 수 있게 합니다.
- 판단: 현재 동작이 사용자 목적과 설계 기준을 따르도록, 의미를 결정하는 책임을 분명히 합니다.
- 맥락: 결정 이유와 검증 상태, 다음 행동이 세션과 에이전트를 넘어 이어지게 합니다.
설치한 뒤 새 작업을 시작하세요. Codex는 요청에서 드러난 문제에 맞는 스킬을 선택합니다.
- structure-first: 흐름·상태·책임·조합이나 경계 계약이 달라지는 코드 변경을 읽고 검증하기 쉽게 유지하며, 여러 표현에 걸친 확정 의미의 해석과 번역 경계도 한 owner에 둡니다.
- project-context: 장기 작업의 목표와 판단, 현재 상태와 다음 행동을 저장소에 남겨 세션과 에이전트 사이에서 이어갑니다.
- purpose-first-design: 제품 의미나 구현 계획의 방향이 실질적으로 열려 있을 때 새 기능·재사용 선택·임시 구현 등 중대한 선택의 초기 방향을 목적과 확정된 경계에서 정하고, 답변이 만든 불필요한 범위와 약속을 줄입니다.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 9
- MCP servers
- 0
- Stars
- 5
- License
- MIT
- Repo created
- 2026-07-10
- Last pushed
- 2026-10-20
- Publisher type
- User
- Version
- 0.17.1
Links
Skills · 9
- agent-cost-efficiency
- Use for agent work with clear excess-cost risk: broad or unpredictable logs and diffs, browser/UI loops, costly execution/retry loops and progress observation even with small output, costly or repeated delegation, or repeated compaction. Guides bounded execution and observation, preflight output li…
- agents-md-editor
- Use when creating, editing, or reviewing AGENTS.md, agents.md, CLAUDE.md, Copilot instructions, Cursor rules, or any always-read repository instruction file. Keep persistent agent instructions small, durable, non-duplicative, and action-oriented; classify content that belongs in commands, onboardin…
- interactive-state-flow
- Use when an interactive flow is laggy, stale, or race-prone because user intent, source state, derived presentation, async IO, scheduling, or background work are mixed. Keep source state prompt, protect the urgent interaction path, and admit async or presentation results only through a freshness-ow…
- project-context-migration
- Audit scattered repository docs and notes, then move only the right working context into the `project-context` structure.
- project-context
- Resume, handoff, and long-running repo work by keeping durable context across threads or agents: task briefs, logs, and reusable reference notes.
- purpose-first-design
- Use when product meaning or implementation-planning direction is materially open before solution structure is settled, including early direction for a new feature, reuse choices, temporary implementations, or another materially consequential product or implementation-planning choice. Choose a bound…
- source-owner-audit
- Use for read-only source-of-truth audits: identify the current code, API, config, doc, or behavior to follow; compare a proposed, migrated, ported, or current change against it; and report evidence, mismatches, unresolved decisions, and owner-level recommendations.
- structure-first
- Use for code generation, feature work, bug fixes, refactoring, and code review when a change creates or reshapes a multi-step flow, state lifecycle, side-effect or decision ownership, cross-unit composition, or boundary contract. Also use it when an existing structural problem makes those elements…
- tighten-docs
- Use by default whenever creating, revising, reviewing, or finalizing human-authored documentation whose source meaning is settled, including documentation changed within another task. Apply from first draft through final review to keep one direct current state, clear reader routes and ownership, an…
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
codex · claude-code · project-context · software-development · maintainability · documentation · verification
Related by publisher and keywords
Intent to implementation: ready, then go.
Software documentation specialist with arc42 DESIGN_DOC.md, architecture docs, Mermaid-first diagrams, and PlantUML Salt UI wireframes. STE100 default. Google docs style on request. Claude Code, Grok Build, Codex, Cursor, and Agent Plugins 1.0.
Independently falsify or approve implementation plans before execution with ACCEPT, MODIFY, or REJECT verdicts per task or decision gate.
Portable skills for repository setup, private remote development, code-native design exploration, design-system alignment and auditing, UI video analysis, mobile performance tuning, Apple system integration, feature validation and delivery, and technical documentation.
Universal agent plugin for Google developer documentation style. Skills, a custom output formatter, and hooks for Claude Code, Codex, Cursor, and Grok Build.
Unified multi-platform marketplace plugin bundling document-specialist, Mermaid, PlantUML, imagen-diagrams, Google Docs style, and STE 100 skills. Mermaid-first diagrams. PlantUML for wireframes and leftover UML. imagen-diagrams for themed slide and article figures. Supports Claude Code, Codex, Grok Build, Cursor, and universal plugin standard.
[](https://agentpluginsdirectory.com/plugins/project-legibility)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.