perhapsspy

perhapsspy/project-legibility

Instructions file CodexOpenCode

Instructions for perhapsspy/project-legibility, covering agents.md and 검증.

perhapsspy/project-legibility

Skill Claude CodeCodex

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, onboarding, reference docs…

perhapsspy/project-legibility

Skill Claude CodeCodex

Invoke explicitly with $codex-project-director to act as an active, non-implementing control plane that drives multiple Codex tasks or sessions toward one verified project outcome. Use only for a user-designated director or supervisor session, not a single local task, ordinary implementation, one-off review, or status…

perhapsspy/project-legibility

Skill Claude CodeCodex

Use for Codex work with clear excess-cost risk: broad or unpredictable logs and diffs, browser/UI loops, subagents, repeated compaction, or explicit usage audits. Guides preflight output limits, bounded delegation, evidence reuse, and compact checkpoints. Skip routine edits, direct answers, and ordinary test runs.

perhapsspy/project-legibility

Skill Claude CodeCodex

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-owning boundary.

perhapsspy/project-legibility

Skill Claude CodeCodex

Audit scattered repository docs and notes, then move only the right working context into the project-context structure.

perhapsspy/project-legibility

Skill Claude CodeCodex

Resume, handoff, and long-running repo work by keeping durable context across threads or agents: task briefs, logs, and reusable reference notes.

perhapsspy/project-legibility

Skill Claude CodeCodex

Use to set an early design or implementation-planning direction from user/domain purpose, explicit constraints, current evidence, and verifiable success conditions. Apply to new features, reuse decisions, and temporary implementations when existing code, precedent, defaults, or urgency could steer the choice. Direct…

perhapsspy/project-legibility

Skill Claude CodeCodex

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.

perhapsspy/project-legibility

Skill Claude CodeCodex

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 hard to trace or…

perhapsspy/project-legibility

Skill Claude CodeCodex

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, and remove rejected…