AI Context — Data & AI agent for Claude Code
Compresses discovery output into the single structured task-context document every later agent reads instead of the repository.
How to install AI Context
Installs to ~/.claude/agents/vanssata-claude-agentic-sdlc-module-ai-context.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vanssata/claude-agentic-sdlc-module/HEAD/agents/ai-context.md -o ~/.claude/agents/vanssata-claude-agentic-sdlc-module-ai-context.md Restart Claude Code, or start a new session, for it to be picked up.
What AI Context does
name: ai-context description: Compresses discovery output into the single structured task-context document every later agent reads instead of the repository. Use after discovery, before planning. Returns a fixed-shape summary, no prose. tools: Read, Grep, Glob disallowedTools: Edit, Write, NotebookEdit model: sonnet effort: medium color: cyan
You turn scattered findings into one document that stands on its own, so that the planner, the reviewer and the security agent never need the disco
Alternatives in Data & AI
- Claude Mem — A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresse 38.9k ★
- Svelte Correctness Review — Reviews a feature segment in any SvelteKit app (apps/moderator, apps/auth, apps/creator-studio) for correctnes 7.2k ★
- Comprehension Review — De-warmed cold comprehension-and-structure gate for design.md and track files: reads only the document, never 432 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
DB Migration Specialist
Schema migration specialist for any storage layer (SQL, ORMs, Room, document stores). Use when a change adds/a
AI Indexer
Cheapest possible repository inventory — file listings, symbol extraction, git-log summaries, counting and tab
AI Risk
Assigns exactly one risk tier T0–T5 to a proposed change, from .ai/policies/risk-tiers.json, and says which tr
Session Error Analyzer
Analyzes specific AI IDE sessions (Claude Code, OpenAI Codex, OpenCode) for LLM behavior errors and returns a
Miner
Parses structured data at volume — JSONL transcripts, logs, ledgers, CSV, counters — and returns the extracted
API Troubleshooter
Layer-2 diagnostic agent for API/controller failures. Use when: unexpected status codes, curl vs browser diver
Related Skills
Claude Session Recall
A Claude Code skill that reads your session's own transcript, so a fact that arrived through a compaction summ
Report To Brief
긴 보고서를 정책브리프·요약본(1~8p)으로 압축하는 Claude Code 스킬 — 두괄식·자립성·근거보존, 3축 압축검수로 요약 환각 차단 Compresses long reports into st
Lm Resizer
Rust-native context compression for Claude Code, Codex & MCP agents: filters & compresses noisy tool output (t