Playbooks · Agent context
Inject scoped context at session start
Use a SessionStart hook to supply fixed context needed for the task and verify what was injected each run.
FREE AGENT SKILLS · MCP · AUTOMATION
Playbooks
Free public resources
Agent artifactsAgent authorizationAgent contextAgent evaluationAgent interoperabilityAgent memoryAgent observabilityAgent operationsAgent orchestrationAgent outputAgent recoveryAgent reliabilityAgent researchAgent runtimeAgent safetyAgent setupAgent stateAgent toolsAgent workflowsContent automationCrypto quant researchCrypto quant workflowsData automationDocument automationDocument and data automationMCP clientsMCP reliabilityMCP resourcesMCP serversMCP testingRetrievalSkill authoring
Playbooks · Agent context
Disable session snapshots while iterating on a system prompt
Use snapshot=False in system_prompt so prompt edits apply per request, separating iteration from stable sessions.
Playbooks · Agent tools
Provide an in-process read-only MCP tool
Wrap a narrow Python function as an SDK MCP server and allow only its named tool.
Playbooks · Agent operations
Set a USD budget cap for an agent run
Use max_budget_usd to cap a run’s cost and detect the budget-exceeded terminal status.
Playbooks · Agent operations
Classify agent failures by structured exception
Separate missing CLI, connection loss, process failure, and terminal model errors instead of retrying every exception.
Playbooks · Agent operations
Capture CLI stderr diagnostics
Use the stderr callback to collect warning and error lines for CLI or connection diagnosis.
Playbooks · Agent memory
Validate a custom session store with the conformance suite
Run the SDK’s SessionStore contract suite before connecting an external transcript backend.
Playbooks · Agent memory
Store and resume a session transcript in private S3
Use the reference S3 SessionStore to mirror session messages and resume a conversation by session ID.
Playbooks · Agent memory
Set retention and deletion policy for persisted sessions
Define an enforceable retention period for transcripts covering object lifecycle and explicit deletion.
Playbooks · Agent output
Get a JSON Schema-shaped agent result
Set output_format and read structured data from the terminal ResultMessage.structured_output.
Playbooks · Agent workflows
Schedule read-only repository reviews and verify finding continuity
Run recurring reviews with structured verdicts/findings and have each follow-up prove which prior issues remain.
Playbooks · Agent workflows
Turn SRE incident evidence into a verifiable response brief
Use a focused agent to synthesize alerts, logs, and read-only checks while separating facts, hypotheses, and next verification.
Playbooks · Agent research
Return traceable citations for document question answering
Provide documents as trusted sources and preserve source locations in answers instead of asking the model to invent citations.
Playbooks · Document automation
Extract validated fields from unstructured documents
Convert documents into fixed-field JSON records while keeping validation in the application.
Playbooks · Agent workflows
Break an open-ended writing task into parallel drafts
Let an orchestrator choose task-specific angles and specialized workers produce comparable drafts.
Playbooks · Agent evaluation
Improve a code draft with explicit pass criteria
Have a generator implement a task, an evaluator score only against criteria, and iterate within a bounded loop.
Playbooks · Retrieval
Answer internal knowledge questions from retrieved chunks
Chunk internal documents by heading, retrieve multiple relevant passages, then synthesize with source locations.
Playbooks · Agent evaluation
Measure RAG retrieval and final-answer quality separately
Use questions with gold source labels to compute retrieval Precision/Recall/MRR separately from end-to-end accuracy.
Playbooks · Retrieval
Add document context to chunks before indexing
Generate a short contextual description for each chunk and embed it with the original text to improve retrieval of context-poor passages.
Playbooks · Agent tools
Use semantic retrieval to select tools from a large library
Embed tool descriptions locally and retrieve relevant capabilities for the current task through one narrow search tool.
Playbooks · Document automation
Build an entity graph to answer cross-document questions
Extract typed entities and relation triples, resolve name variants, then answer multi-hop questions over the graph.
Playbooks · Content automation
Classify support tickets with an explanation
Classify clear cases using category definitions, then evaluate ambiguous cases with retrieval context and route them for review.
Playbooks · Content automation
Turn a written content policy into a moderation and escalation flow
Extract typed attributes from policy and use deterministic rules for publish/reject/review rather than letting a model decide final action.
Playbooks · Data automation
Turn natural-language analysis into read-only SQL
Provide the schema of a test database, inspect generated SQL, then execute it only on a read-only replica.
Playbooks · Agent tools
Orchestrate tool calls in batches inside a constrained execution environment
Have the model write code that chains API calls inside a code-execution tool and returns only filtered results.
No matching entries.