{ "schema_version": "1.1", "id": "atlas-context-engineering", "slug": "context-engineering", "title": "Context Engineering", "url": "https://feed7.dev/atlas/context-engineering", "current_answer": "Deciding what belongs in an agent’s context window — and what to leave out — so the model spends its budget on decision-relevant material.", "implementation_consequence": "Most agent failures are context failures: too much noise, missing facts, or stale material. Treating context as a ranked budget makes sessions repeatable.", "agent_context": "Treat context as a budget, not a dump. Rank material by decision-relevance; evict anything that does not change the next action. Isolate noisy subtasks into subagents. Cache stable material where the platform allows.", "confidence": "editorial", "last_verified": null, "last_updated": "2026-07-02T00:00:00.000Z", "evidence": [ { "schema_version": "1.1", "id": "p2", "slug": "context-engineering-talk", "url": "https://feed7.dev/p/context-engineering-talk", "title": "Context engineering for coding agents — AI Engineer World’s Fair", "why_included": "A reusable framework for deciding what belongs in an agent’s context window and what to leave out.", "summary": "Introduces a \"context budget\": rank material by decision-relevance, evict anything that does not change the next action. Includes a worked example on a real repo.", "practical_implication": "Practical, tool-agnostic, testable. Apply the budget per session instead of dumping everything into the window.", "agent_context": "Treat context as a budget, not a dump. Rank material by decision-relevance; evict anything that does not change the next action. Works across Cursor, Claude Code, Codex.", "source": { "name": "AI Engineer", "url": "https://www.youtube.com/watch?v=ai-eng-context-2026", "published_at": "2026-06-28T00:00:00.000Z" }, "source_class": "video", "content_type": "AI Engineer Talk", "layer": "context", "domains": [ "coding" ], "topics": [ "context-engineering" ], "verification": { "status": "transcript_verified", "label": "Transcript Verified", "method": "transcript_review", "verified_at": null }, "uncertainty": [ "Framework is presenter’s own; not yet independently benchmarked." ], "connected_context": null, "lifecycle": "Evergreen", "published_at": "2026-06-28T00:00:00.000Z", "modified_at": "2026-06-28T00:00:00.000Z", "supersedes": [], "expires_at": null, "formats": { "html": "https://feed7.dev/p/context-engineering-talk", "json": "https://feed7.dev/p/context-engineering-talk.json", "markdown": "https://feed7.dev/p/context-engineering-talk.md" } }, { "schema_version": "1.1", "id": "p1", "slug": "claude-code-subagents", "url": "https://feed7.dev/p/claude-code-subagents", "title": "Claude Code ships subagents in isolated context windows", "why_included": "Long refactors no longer pollute the parent context — a child agent does the noisy work and reports back.", "summary": "Subagents get their own context window and a clean handoff contract. The parent session receives only the result summary and the list of touched files.", "practical_implication": "Fewer derailed sessions on big tasks. Route any task over ~20 file edits to a subagent and keep your planning context clean.", "agent_context": "Claude Code subagents run in isolated context. Use them for long refactors and research sweeps: the parent stays clean while a child does the noisy work, then reports which files remain. Prefer for tasks >20 file edits.", "source": { "name": "Anthropic", "url": "https://www.anthropic.com/engineering/claude-code-subagents", "published_at": "2026-07-02T00:00:00.000Z" }, "source_class": "blog_post", "content_type": "Official Release", "layer": "tools", "domains": [ "coding" ], "topics": [ "subagents", "coding-agents" ], "verification": { "status": "official_source", "label": "Official Source", "method": "source_feed", "verified_at": null }, "uncertainty": [], "connected_context": null, "lifecycle": "New", "published_at": "2026-07-02T00:00:00.000Z", "modified_at": "2026-07-02T00:00:00.000Z", "supersedes": [], "expires_at": null, "formats": { "html": "https://feed7.dev/p/claude-code-subagents", "json": "https://feed7.dev/p/claude-code-subagents.json", "markdown": "https://feed7.dev/p/claude-code-subagents.md" } }, { "schema_version": "1.1", "id": "p9", "slug": "gemini-context-caching", "url": "https://feed7.dev/p/gemini-context-caching", "title": "Gemini agent SDK adds shared context caching across sessions", "why_included": "Cached context is billed once and reused across agent sessions — changes the economics of long system prompts.", "summary": "The agent SDK now exposes cross-session context caching with explicit TTL control. Cached tokens are ~10x cheaper on reuse.", "practical_implication": "Big static context (style guides, schemas, docs) belongs in the cache, not the prompt. Restructure bundles so stable material leads.", "agent_context": "Gemini SDK caches context across sessions with TTL control; cached tokens ~10x cheaper. Put stable material (guides, schemas) first so it caches; keep volatile material last.", "source": { "name": "Google", "url": "https://developers.googleblog.com/gemini-agent-sdk-context-cache", "published_at": "2026-06-29T00:00:00.000Z" }, "source_class": "blog_post", "content_type": "Docs Update", "layer": "context", "domains": [ "coding" ], "topics": [ "context-caching" ], "verification": { "status": "official_source", "label": "Official Source", "method": "source_feed", "verified_at": null }, "uncertainty": [], "connected_context": null, "lifecycle": "New", "published_at": "2026-06-29T00:00:00.000Z", "modified_at": "2026-06-29T00:00:00.000Z", "supersedes": [], "expires_at": null, "formats": { "html": "https://feed7.dev/p/gemini-context-caching", "json": "https://feed7.dev/p/gemini-context-caching.json", "markdown": "https://feed7.dev/p/gemini-context-caching.md" } }, { "schema_version": "1.1", "id": "p11", "slug": "ctxlint-repo", "url": "https://feed7.dev/p/ctxlint-repo", "title": "ctxlint: a linter for agent context files", "why_included": "Lints CLAUDE.md / AGENTS.md / rules files for staleness, contradiction, and dead links.", "summary": "CLI that checks agent context files: flags stale dates, contradicting rules, dead links, and files over a token budget. CI-ready. Repo builds and tests pass.", "practical_implication": "Context files rot silently. Run ctxlint in CI so your agent instructions stay as maintained as your code.", "agent_context": "ctxlint lints agent context files (CLAUDE.md, AGENTS.md): staleness, contradictions, dead links, token budget. Add to CI beside your linter.", "source": { "name": "GitHub", "url": "https://github.com/ctxtools/ctxlint", "published_at": "2026-06-23T00:00:00.000Z" }, "source_class": "tool", "content_type": "GitHub Repo", "layer": "context", "domains": [ "coding" ], "topics": [ "context-engineering" ], "verification": { "status": "repo_verified", "label": "Repo Verified", "method": "repo_review", "verified_at": null }, "uncertainty": [ "Maintained by a single author; bus factor 1." ], "connected_context": null, "lifecycle": "New", "published_at": "2026-06-23T00:00:00.000Z", "modified_at": "2026-06-23T00:00:00.000Z", "supersedes": [], "expires_at": null, "formats": { "html": "https://feed7.dev/p/ctxlint-repo", "json": "https://feed7.dev/p/ctxlint-repo.json", "markdown": "https://feed7.dev/p/ctxlint-repo.md" } } ], "conflicting_sources": [], "superseded_claims": [], "corpus_evidence": [ { "title": "Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning", "url": "https://www.youtube.com/watch?v=2bvtay8wGYI", "source_name": "AI Engineer", "published_at": "2026-07-31T21:30:06+00:00", "summary": "Long-running agents strain context, reward design, and GPU scheduling at once. Compaction and value models can help, but each introduces another optimization trade-off." }, { "title": "Vercel MCP now supports the 2026-07-28 MCP specification", "url": "https://vercel.com/changelog/vercel-mcp-now-supports-the-2026-07-28-mcp-specification", "source_name": "Vercel", "published_at": "2026-07-31T00:00:00+00:00", "summary": "Vercel MCP now serves the 2026-07-28 and 2025 protocols from one endpoint, letting newer clients adopt stateless requests and revised authorization without breaking older setups." }, { "title": "ReToken: One Token to Improve Vision-Language Models for Visual Retrieval", "url": "https://arxiv.org/abs/2607.28627v1", "source_name": "arXiv", "published_at": "2026-07-30T17:59:56+00:00", "summary": "ReToken adds one learned retrieval embedding to select relevant visual tokens from a cached context, improving long-image and video benchmarks while fitting training and inference on one H100." }, { "title": "AISPA: User-Centric System Prompt Auditing for Large Language Model Applications", "url": "https://arxiv.org/abs/2607.28617v1", "source_name": "arXiv", "published_at": "2026-07-30T17:58:58+00:00", "summary": "AISPA turns system-prompt review into an eight-dimension audit. Its survey suggests builders should test prompts for user protection and conflicting instructions, not merely check that safeguards exist." }, { "title": "Let's integrate AI Agents in Event-Sourced Systems — Divakar Kumar, FlyersSoft", "url": "https://www.youtube.com/watch?v=o6U_2vd967Y", "source_name": "AI Engineer", "published_at": "2026-07-30T00:00:06+00:00", "summary": "Add agents beside deterministic fraud systems, not in place of them: project cross-service events into a semantic layer, send only uncertain cases to specialist agents, then emit the verdict back into the saga." }, { "title": "Latest MCP spec now supported in mcp-handler", "url": "https://vercel.com/changelog/latest-mcp-spec-now-supported-in-mcp-handler", "source_name": "Vercel", "published_at": "2026-07-30T00:00:00+00:00", "summary": "mcp-handler 2.0 adds the stateless 2026 MCP protocol and SDK v2 while keeping 2025 Streamable HTTP clients working, but drops HTTP+SSE and raises upgrade requirements." }, { "title": "Wearing the Agent: From Group Chats to Glasses — Sai Krishna Rallabandi", "url": "https://www.youtube.com/watch?v=s67bE2Ur3bY", "source_name": "AI Engineer", "published_at": "2026-07-29T22:58:19+00:00", "summary": "Shared agents need a different harness: action-boundary security, selective group memory, per-user privacy, and routing that decides both who receives information and when the agent should speak." }, { "title": "Skills are new features: Building Skill-Centric Harness — Yogendra Miraje, FactSet", "url": "https://www.youtube.com/watch?v=7jjudsEhBtM", "source_name": "AI Engineer", "published_at": "2026-07-29T18:00:06+00:00", "summary": "FactSet treats skills as versioned product features and the harness as their runtime. Routing descriptions, model-specific evals, access controls, and governance matter as libraries grow." }, { "title": "AI tools for Forward Deployed Engineering — Vasuman Moza, Varick Agents", "url": "https://www.youtube.com/watch?v=l0FLhNqBOic", "source_name": "AI Engineer", "published_at": "2026-07-28T21:00:06+00:00", "summary": "Varick treats enterprise agents as process-reengineering systems: capture how work really happens, encode that context, then automate only the steps whose risk permits it." }, { "title": "How Forward Deployed Engineering is done at Ramp — Leo Mehr", "url": "https://www.youtube.com/watch?v=ITMXwI6QL6A", "source_name": "AI Engineer", "published_at": "2026-07-28T19:00:06+00:00", "summary": "Ramp pairs strict request scoping with agents across the delivery pipeline. Its intake agent reportedly saves about 20% of scoping time, while humans retain final judgment." }, { "title": "UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams", "url": "https://arxiv.org/abs/2607.26017v1", "source_name": "arXiv", "published_at": "2026-07-28T17:28:21+00:00", "summary": "UniMem routes novel experience into retrieval memory and consolidates recurring patterns into expandable parameters, offering a design for agents that learn across unlabelled task streams." }, { "title": "Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?", "url": "https://arxiv.org/abs/2607.25995v1", "source_name": "arXiv", "published_at": "2026-07-28T17:12:12+00:00", "summary": "Kubernetes security patches improved sharply when the model received live service dependencies, showing that scanner findings alone omit context needed to avoid breaking workloads." }, { "title": "How Forward Deployed Engineering is done at Decagon — Sunny Rekhi", "url": "https://www.youtube.com/watch?v=7wu2hsRfvV0", "source_name": "AI Engineer", "published_at": "2026-07-28T17:00:35+00:00", "summary": "Decagon splits deployment between configuring each customer’s agent and turning repeated enterprise requests into product features. The scarce skill is resisting brittle one-offs." }, { "title": "How Forward Deployed Engineering is done at Kepler — Vinoo Ganesh", "url": "https://www.youtube.com/watch?v=1OMHGsUZiqA", "source_name": "AI Engineer", "published_at": "2026-07-28T16:00:00+00:00", "summary": "Kepler frames forward deployment as product discovery: observe real work, ship the smallest useful fix, then turn repeated pain and customer vocabulary into durable product leverage." }, { "title": "AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j", "url": "https://www.youtube.com/watch?v=kRkcNOsRyYg", "source_name": "AI Engineer", "published_at": "2026-07-23T07:00:23+00:00", "summary": "Graph-shaped context can expose relationships and document structure that vector search or Text-to-SQL misses. Treat it as an additional retrieval surface, then benchmark it against your own data." }, { "title": "Citation Needed: Provenance for LLM-Built Knowledge Graphs — Daniel Chalef, Zep AI", "url": "https://www.youtube.com/watch?v=H7puB0RwJMM", "source_name": "AI Engineer", "published_at": "2026-07-23T04:00:02+00:00", "summary": "LLM synthesis breaks simple source pointers when facts merge, change, or outlive one input. Model provenance inside the context graph so agents can filter trust, debug derivation, and apply deletion policies." }, { "title": "WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar", "url": "https://www.youtube.com/watch?v=8G_1-3IO4ZQ", "source_name": "AI Engineer", "published_at": "2026-07-14T22:45:06+00:00", "summary": "Atlan’s agent experiments argue for shared, versioned context instead of per-agent memory: a portable layer for business facts, skills, norms, retrieval, and feedback across changing harnesses." }, { "title": "Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution", "url": "https://arxiv.org/abs/2607.13034v1", "source_name": "arXiv", "published_at": "2026-07-14T17:59:31+00:00", "summary": "E3 makes agents estimate task scope, try the minimum viable path, and expand only after verification fails. In a controlled edit benchmark, it preserved task completion while sharply reducing work." }, { "title": "The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context", "url": "https://arxiv.org/abs/2607.12963v1", "source_name": "arXiv", "published_at": "2026-07-14T17:01:12+00:00", "summary": "Stable aggregate accuracy can hide individual answers flipping when irrelevant context is added. Agent evaluations should compare outputs per task and probe realistic context noise, not only average scores." }, { "title": "TencentCloud/TencentDB-Agent-Memory", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory", "source_name": "GitHub", "published_at": null, "summary": "An open-source memory hub turns agent conversations, workflows, docs, and code into governed assets that can be reused across sessions and roles, reducing repeated project setup." }, { "title": "virgiliojr94/book-to-skill", "url": "https://github.com/virgiliojr94/book-to-skill", "source_name": "GitHub", "published_at": null, "summary": "book-to-skill compiles books and document sets into on-demand agent skills, reducing repeated context loading while preserving chapter-level references and reusable decision rules." }, { "title": "How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?", "url": "https://arxiv.org/abs/2607.11783v1", "source_name": null, "published_at": null, "summary": "A RAG study finds that retrieved ideology carries into answers and varies with sampling temperature, so source audits and decoding tests should be evaluated together." }, { "title": "RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI", "url": "https://www.youtube.com/watch?v=8oyalrfwgjw", "source_name": null, "published_at": null, "summary": "RLMs treat a large repository as external data that an agent inspects with code, returning bounded evidence to the main context instead of loading or summarizing everything upfront." }, { "title": "Graphify-Labs/graphify", "url": "https://github.com/Graphify-Labs/graphify", "source_name": null, "published_at": null, "summary": "Graphify gives coding agents a queryable project graph with provenance-tagged relationships, reducing repeated repository scans while keeping inferred links visibly distinct from extracted facts." }, { "title": "CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents", "url": "https://arxiv.org/abs/2607.05378v1", "source_name": null, "published_at": null, "summary": "CompactionRL uses RL to teach agents to compact their own context mid-task, lifting GLM-4.5-Air 7 points to 66.8% on SWE-bench Verified; the recipe is now in GLM-5.2's training pipeline." }, { "title": "ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning", "url": "https://arxiv.org/abs/2607.02509v1", "source_name": null, "published_at": null, "summary": "ReContext is a training-free harness that replays query-relevant evidence from long inputs before answering, taking the best average rank across 8 long-context benchmarks up to 128K on Qwen3-4B/8B and Llama3-8B." }, { "title": "coreyhaines31/marketingskills", "url": "https://github.com/coreyhaines31/marketingskills", "source_name": null, "published_at": null, "summary": "Marketing Skills gives coding agents shared product context and task-specific workflows for CRO, copy, SEO, analytics, pricing, and launch work, reducing repeated setup across growth tasks." }, { "title": "asgeirtj/system_prompts_leaks", "url": "https://github.com/asgeirtj/system_prompts_leaks", "source_name": null, "published_at": null, "summary": "A maintained archive of extracted system prompts from 100+ AI products — Claude Fable 5, Claude Code, ChatGPT 5.5, Gemini, Cursor — useful for studying how vendors actually instruct their agents." } ] }