Hook
Runs before the agent uses a tool for Bash, Bash, Read, Edit, Write, MultiEdit, Glob, Grep, NotebookEdit, mcp__filesystem__.*, Edit, Write, MultiEdit, Bash and Bash tool calls, executing guard-destructive.sh, guard-path.sh, guard-config.sh, commit-quality.sh and revert-guard.sh (5 commands). From softspark/ai-toolkit.
Hook
Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.sh and track-usage.sh (2 commands). From softspark/ai-toolkit.
Hook
Runs after a tool call finishes for Edit, MultiEdit, Write, Bash, Edit, Write, MultiEdit, Bash, Edit, MultiEdit, Write, Edit, MultiEdit, Write, mcp__.*__(smart_query, hybrid_search_kb, crag_search, multi_hop_search, verify_answer), WebSearch and WebFetch tool calls, executing post-tool-use.sh, governance-capture.sh…
Hook
Runs when the agent finishes a response, executing quality-check.sh, save-session.sh, quality-gate.sh and stop-search-check.sh (4 commands). From softspark/ai-toolkit.
Hook
Runs when a task is marked completed, executing quality-gate.sh. From softspark/ai-toolkit.
Hook
Runs on the TeammateIdle event, running echo 'Teammate going idle. Verify: (1) All assigned files mo. From softspark/ai-toolkit.
Hook
Runs when a subagent starts, executing subagent-start.sh. From softspark/ai-toolkit.
Hook
Runs when a subagent finishes, executing subagent-stop.sh. From softspark/ai-toolkit.
Hook
Runs before the context is compacted, executing pre-compact.sh and pre-compact-save.sh (2 commands). From softspark/ai-toolkit.
Hook
Runs when a session ends, executing session-end.sh. From softspark/ai-toolkit.
Hook
Runs after instructions files are loaded, executing instructions-audit.sh. From softspark/ai-toolkit.
Hook
Runs on the ConfigChange event for user_settings tool calls, executing config-desync-guard.sh. From softspark/ai-toolkit.
Skill Claude CodeCodex
Mandatory engineering, security, testing, git, performance, quality, and response rules. Claude MUST load this skill for every technical, coding, debugging, review, architecture, DevOps, data, or file-editing task in Chat or Cowork.
Skill Claude CodeCodex
Search past coding sessions using natural language. Finds relevant observations, decisions, and context from previous work.
Skill Claude CodeCodex
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. Triggers: a11y, accessibility, WCAG, EAA, ARIA, contrast, keyboard, screen reader.
Skill Claude CodeCodex
Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent, create agent, agent scaffold, specialized agent.
Skill Claude CodeCodex
Analyzes code quality, complexity, patterns across codebase. Triggers: quality report, hotspot scan, code analysis, architecture signal.
Skill Claude CodeCodex
REST/GraphQL API design: naming, versioning, pagination, idempotency, OpenAPI. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, idempotency, rate limit.
Skill Claude CodeCodex
App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter. Triggers: scaffold, bootstrap, new project, starter, dashboard, mobile app.
Skill Claude CodeCodex
Audits codebase for architectural friction, shallow modules; proposes RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling.
Skill Claude CodeCodex
Architecture decisions in ADR/RFC/RFD format: context, constraints, options, recommendation. Triggers: ADR, RFC, RFD, trade-offs, design choice, pick between, evaluate approach.
Skill Claude CodeCodex
Scans codebase for revenue opportunities, KPIs, monetization gaps. Triggers: business metrics, KPI, analytics gaps, monetization, revenue.
Skill Claude CodeCodex
Pre-artifact conversation that prices the zero option and can end in 'do not build this'. Triggers: brainstorm, should we build, is this worth it, explore idea, thinking out loud, half-formed idea.
Skill Claude CodeCodex
Direct technical voice for docs, README, user-facing text. Concise/strict modes. Triggers: documentation, README, content, output-mode, voice, prose style.