Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/anthropics/claude-cookbooks
/ functions
Functions
640 in github.com/anthropics/claude-cookbooks
⨍
Functions
640
◇
Types & classes
67
↳
Endpoints
7
↓ 1 callers
Function
main
()
scripts/test_notebooks.py:112
↓ 1 callers
Function
main
Main entry point.
scripts/validate_all_notebooks.py:774
↓ 1 callers
Function
main
()
capabilities/knowledge_graph/evaluation/eval_extraction.py:90
↓ 1 callers
Function
main
Example usage demonstrating brand validation
skills/custom_skills/applying-brand-guidelines/validate_brand.py:273
↓ 1 callers
Function
main
* One-time provisioning. Creates, in order: * * environment a cloud sandbox that can reach exactly two hosts * reviewer a second agent:
managed_agents/roadtrip_planner/setup/create.ts:29
↓ 1 callers
Function
main
()
managed_agents/roadtrip_planner/setup/teardown.ts:24
↓ 1 callers
Function
main
()
managed_agents/self_hosted_sandboxes/modal/sandbox_runner.py:50
↓ 1 callers
Function
mean
(xs)
managed_agents/example_data/iterate/calc.py:9
↓ 1 callers
Function
mergeLog
Append log events the array does not have yet. The log's order wins.
managed_agents/roadtrip_planner/src/lib/use-managed-agent-session.ts:33
↓ 1 callers
Function
newTransport
()
managed_agents/cma-mcp/src/server-http.ts:17
↓ 1 callers
Function
nltk_bleu_eval
Calculate BLEU score using NLTK and evaluate against a threshold. Args: output (str): The output to evaluate. ground_truth (str): Th
capabilities/summarization/evaluation/custom_evals/bleu_eval.py:12
↓ 1 callers
Method
one_way_sensitivity
Perform one-way sensitivity analysis. Args: variable_name: Name of variable to test base_value: Base case va
skills/custom_skills/creating-financial-models/sensitivity_analysis.py:27
↓ 1 callers
Function
pagerduty_create_incident
Create a PagerDuty incident.
claude_agent_sdk/site_reliability_agent/sre_mcp_server.py:1574
↓ 1 callers
Function
pagerduty_get_incident
Get PagerDuty incident details.
claude_agent_sdk/site_reliability_agent/sre_mcp_server.py:1734
↓ 1 callers
Function
pagerduty_list_incidents
List PagerDuty incidents.
claude_agent_sdk/site_reliability_agent/sre_mcp_server.py:1788
↓ 1 callers
Function
pagerduty_update_incident
Update a PagerDuty incident status.
claude_agent_sdk/site_reliability_agent/sre_mcp_server.py:1661
↓ 1 callers
Function
parse_alpha
claude_agent_sdk/vulnerability_detection_agent/canary/canary.c:7
↓ 1 callers
Function
parse_bravo
claude_agent_sdk/vulnerability_detection_agent/canary/canary.c:14
↓ 1 callers
Function
parse_charlie
claude_agent_sdk/vulnerability_detection_agent/canary/canary.c:21
↓ 1 callers
Function
parse_content_block
Parse a single content block from a message.
tool_use/utils/visualize.py:41
↓ 1 callers
Function
postTerminationError
(claudeSessionId: string)
managed_agents/linear/src/cma-webhook.ts:80
↓ 1 callers
Function
prf
(predicted: set, gold: set)
capabilities/knowledge_graph/evaluation/eval_extraction.py:82
↓ 1 callers
Function
processWorkItem
Ack and create a sandbox for one work item. * Raises on ack failure or Vercel API errors — the caller treats any raise * as "skip this item and keep
managed_agents/self_hosted_sandboxes/vercel/api/webhook.ts:150
↓ 1 callers
Method
process_batch
Process multiple files concurrently. MULTIPLE BUGS: 1. self.processed_count is incremented without locking 2. self.r
tool_use/memory_demo/sample_code/data_processor_v1.py:41
↓ 1 callers
Function
process_investigation
Process the investigation in the background, streaming output to Slack. Args: incident_text: The incident description or follow-up reques
claude_agent_sdk/site_reliability_agent/examples/sre_bot_slack.py:401
↓ 1 callers
Function
process_ticket
Process a ticket: assign priority and team
tool_use/utils/customer_service_api.py:273
↓ 1 callers
Function
query_metrics
Query Prometheus with a PromQL expression.
claude_agent_sdk/site_reliability_agent/sre_mcp_server.py:629
↓ 1 callers
Function
rank_candidates
Rank multiple candidates
claude_agent_sdk/chief_of_staff_agent/scripts/talent_scorer.py:105
↓ 1 callers
Function
read_config_file
Read a configuration file from the project directory.
claude_agent_sdk/site_reliability_agent/sre_mcp_server.py:2214
↓ 1 callers
Method
read_from_s3
Write a JSON object to an S3 bucket :param bucket_name: Name of the S3 bucket :param file_name: Name of the file to be creat
capabilities/contextual-embeddings/contextual-rag-lambda-function/s3_adapter.py:43
↓ 1 callers
Function
redact
Scrub credential shapes before mirroring an error message to the function log.
managed_agents/self_hosted_sandboxes/cf/src/index.ts:24
↓ 1 callers
Function
redact
Scrub credential shapes before mirroring sandbox output to the function log.
managed_agents/self_hosted_sandboxes/vercel/api/webhook.ts:74
↓ 1 callers
Function
redact
Scrub credential shapes before mirroring an error message to the function log.
managed_agents/self_hosted_sandboxes/cf-worker/src/index.ts:25
↓ 1 callers
Function
relay_sse
POST the request body to the agent pod and return a raw-SSE byte stream. The upstream connection is established **before** this coroutine returns
claude_agent_sdk/hosting/kubernetes/gateway/proxy.py:26
↓ 1 callers
Function
render_code_execution_result
Render a code_execution_tool_result content block.
tool_use/utils/visualize.py:229
↓ 1 callers
Function
render_content_block
Render a single content block based on its type.
tool_use/utils/visualize.py:265
↓ 1 callers
Function
render_server_tool_use
Render a server_tool_use content block.
tool_use/utils/visualize.py:164
↓ 1 callers
Function
render_text_content
Render a text content block.
tool_use/utils/visualize.py:124
↓ 1 callers
Function
render_tool_result
Render a tool_result content block.
tool_use/utils/visualize.py:196
↓ 1 callers
Function
render_tool_use
Render a tool_use content block.
tool_use/utils/visualize.py:135
↓ 1 callers
Function
requireEnv
(name: string, hint?: string)
managed_agents/roadtrip_planner/setup/env.ts:42
↓ 1 callers
Function
requireEnv
(name: string)
managed_agents/self_hosted_sandboxes/vercel/api/webhook.ts:63
↓ 1 callers
Function
retrieve_level_two
(query)
capabilities/retrieval_augmented_generation/evaluation/prompts.py:53
↓ 1 callers
Function
reveal
(groupId: string, callId: string)
managed_agents/roadtrip_planner/src/app/page.tsx:161
↓ 1 callers
Function
rouge_eval
Evaluate summary using ROUGE scores. Args: summary (str): The summary to evaluate. ground_truth (str): The ground_truth summary.
capabilities/summarization/evaluation/custom_evals/rouge_eval.py:7
↓ 1 callers
Method
runWorkItem
* Heartbeat the lease + run the session tool runner; force-stop on exit. * `SessionToolRunner` only owns the dispatch loop, so the work-item lifecy
managed_agents/self_hosted_sandboxes/cf-worker/src/runner.ts:72
↓ 1 callers
Function
run_conversation_turn
Run a single conversation turn, handling tool uses. Args: client: Anthropic client instance model: Model to use mess
tool_use/memory_demo/demo_helpers.py:31
↓ 1 callers
Method
run_progressive_validation
Run validation in batches with user control.
scripts/validate_all_notebooks.py:545
↓ 1 callers
Function
run_pytest
Run pytest with the given arguments.
scripts/test_notebooks.py:98
↓ 1 callers
Function
run_quick_validation
Run quick validation on a single notebook.
scripts/test_notebooks.py:74
↓ 1 callers
Function
run_session_1
Session 1: Learn debugging patterns.
tool_use/memory_demo/code_review_demo.py:204
↓ 1 callers
Function
run_session_2
Session 2: Apply learned patterns.
tool_use/memory_demo/code_review_demo.py:236
↓ 1 callers
Function
run_session_3
Session 3: Long session with context editing.
tool_use/memory_demo/code_review_demo.py:266
↓ 1 callers
Function
run_shell_command
Run a shell command in the project directory.
claude_agent_sdk/site_reliability_agent/sre_mcp_server.py:2321
↓ 1 callers
Function
run_tox
Run tox with the specified environment.
scripts/test_notebooks.py:105
↓ 1 callers
Function
saveEnvLocal
(patch: Record<string, string>)
managed_agents/roadtrip_planner/setup/env.ts:23
↓ 1 callers
Method
scrape_urls
Scrape multiple URLs concurrently. BUG: self.results is accessed from multiple threads without locking! This causes race con
tool_use/memory_demo/sample_code/web_scraper_v1.py:33
↓ 1 callers
Method
search_users
Search users by term. BUG: SQL INJECTION through LIKE clause!
tool_use/memory_demo/sample_code/sql_query_builder.py:42
↓ 1 callers
Function
send_query
Send a query to the research agent with web search and multimodal support. Args: prompt: The query to send activity_handler:
claude_agent_sdk/research_agent/agent.py:69
↓ 1 callers
Method
set_assumptions
Set projection assumptions. Args: projection_years: Number of years to project revenue_growth: Annual revenu
skills/custom_skills/creating-financial-models/dcf_model.py:56
↓ 1 callers
Method
set_historical_financials
Set historical financial data. Args: revenue: Historical revenue ebitda: Historical EBITDA capex
skills/custom_skills/creating-financial-models/dcf_model.py:28
↓ 1 callers
Function
show_diff
Show the difference between current and expected order.
scripts/validate_authors_sorted.py:53
↓ 1 callers
Function
sort_authors
Sort and write authors.yaml. Returns True if file was/would be changed.
scripts/validate_authors_sorted.py:39
↓ 1 callers
Function
start
(fresh: boolean, model?: string)
managed_agents/roadtrip_planner/src/app/page.tsx:51
↓ 1 callers
Function
start_webhook_server
Start the webhook server for PagerDuty events.
claude_agent_sdk/site_reliability_agent/examples/sre_bot_slack.py:642
↓ 1 callers
Function
stream_until_end_turn
Stream a session's events and print until the agent finishes its turn. `session.status_idle` is not always terminal: with `stop_reason.type ==
managed_agents/sentry/cma.py:42
↓ 1 callers
Function
stripMention
(text: string)
managed_agents/slack/src/slack-events.ts:83
↓ 1 callers
Function
submit
(text: string)
managed_agents/roadtrip_planner/src/app/page.tsx:124
↓ 1 callers
Function
summarizeEvent
(e: any)
managed_agents/cma-mcp/src/cma.ts:136
↓ 1 callers
Function
table
(rows: string[], key: string)
managed_agents/roadtrip_planner/src/components/markdown.tsx:53
↓ 1 callers
Function
textOfBlocks
Flatten the text blocks of a Managed Agents content array.
managed_agents/roadtrip_planner/src/lib/transcript.ts:276
↓ 1 callers
Method
tornado_analysis
Create tornado diagram data showing relative impact of variables. Args: variables: Dictionary of variables with base, lo
skills/custom_skills/creating-financial-models/sensitivity_analysis.py:129
↓ 1 callers
Function
update
()
managed_agents/roadtrip_planner/src/app/page.tsx:38
↓ 1 callers
Function
useLingerOpen
* Which items hold themselves open: every live item, plus items whose * stream just ended and are inside the 500ms linger before the collapse * anim
managed_agents/roadtrip_planner/src/components/tool-rail.tsx:38
↓ 1 callers
Function
useManagedAgentSession
(boot: { sessionId: string; events: ManagedAgentEvent[]; working: boolean; })
managed_agents/roadtrip_planner/src/lib/use-managed-agent-session.ts:38
↓ 1 callers
Function
useNarrow
Below 880px the rail becomes a drawer and the header drops its wide-only items.
managed_agents/roadtrip_planner/src/app/page.tsx:34
↓ 1 callers
Method
validate
Perform complete brand validation Returns: ValidationResult
skills/custom_skills/applying-brand-guidelines/validate_brand.py:172
↓ 1 callers
Method
validate_brand_name
Validate brand name usage and capitalization Returns: (violations, warnings)
skills/custom_skills/applying-brand-guidelines/validate_brand.py:121
↓ 1 callers
Method
validate_colors
Validate color usage in content (hex codes, RGB, color names) Returns: (violations, warnings)
skills/custom_skills/applying-brand-guidelines/validate_brand.py:43
↓ 1 callers
Method
validate_fonts
Validate font usage in content Returns: (violations, warnings)
skills/custom_skills/applying-brand-guidelines/validate_brand.py:67
↓ 1 callers
Function
validate_no_empty_cells
Validate that there are no empty cells. Returns a list of warnings (empty cells are often intentional).
tests/notebook_tests/utils.py:150
↓ 1 callers
Function
validate_notebook
Validate a single notebook.
scripts/validate_notebooks.py:14
↓ 1 callers
Method
validate_tone
Validate tone and messaging Returns: (violations, warnings)
skills/custom_skills/applying-brand-guidelines/validate_brand.py:94
↓ 1 callers
Function
validate_uses_env_for_api_key
Validate that API keys are loaded from environment variables. Returns a list of warnings if API key usage doesn't follow best practices.
tests/notebook_tests/utils.py:193
↓ 1 callers
Function
verify
(rawBody: string, headers: Headers)
managed_agents/slack/src/slack-events.ts:13
↓ 1 callers
Function
visualize_conversation_html
Render the full conversation as a styled HTML timeline. Displays system init, tool calls, assistant responses, and subagent delegations
claude_agent_sdk/utils/html_renderer.py:499
↓ 1 callers
Function
wait_for_idle_status
Poll until the session's server-side status field is `idle`. The `session.status_idle` event in the SSE stream can arrive slightly before `se
managed_agents/utilities.py:29
↓ 1 callers
Function
wait_for_idle_status
Poll until the server-side status is `idle`. The `session.status_idle` stream event can arrive slightly before `sessions.retrieve` reports `s
managed_agents/sentry/cma.py:28
↓ 1 callers
Method
write_output_to_s3
Write a JSON object to an S3 bucket :param bucket_name: Name of the S3 bucket :param file_name: Name of the file to be creat
capabilities/contextual-embeddings/contextual-rag-lambda-function/s3_adapter.py:12
↓ 1 callers
Function
write_postmortem
Write a post-mortem report to the postmortems/ directory.
claude_agent_sdk/site_reliability_agent/sre_mcp_server.py:2510
Function
Caret
()
managed_agents/roadtrip_planner/src/components/tool-rail.tsx:168
Function
Chevron
()
managed_agents/roadtrip_planner/src/components/tool-rail.tsx:160
Function
GET
(request: Request)
managed_agents/roadtrip_planner/src/app/api/stream/route.ts:22
Function
Mark
({ size = 22 }: { size?: number })
managed_agents/roadtrip_planner/src/components/mark.tsx:2
Function
Markdown
({ text, streaming = false }: { text: string; streaming?: boolean })
managed_agents/roadtrip_planner/src/components/markdown.tsx:91
Function
POST
(request: Request)
managed_agents/roadtrip_planner/src/app/api/chat/route.ts:11
Function
POST
(request: Request)
managed_agents/roadtrip_planner/src/app/api/session/route.ts:30
Function
POST
()
managed_agents/roadtrip_planner/src/app/api/interrupt/route.ts:10
Function
POST
(req: Request)
managed_agents/self_hosted_sandboxes/vercel/api/webhook.ts:309
Function
Page
()
managed_agents/roadtrip_planner/src/app/page.tsx:46
← previous
next →
301–400 of 640, ranked by callers