{"name":"\/claude-api","slug":"claude-api","family":"slash","title":"Slash commands","noun":"slash command","description":"**[Skill](\/docs\/en\/skills#bundled-skills).** Load [Claude API](https:\/\/platform.claude.com\/docs\/en\/api\/overview) and [Managed Agents](https:\/\/platform.claude.com\/docs\/en\/managed-agents\/overview) reference material for your project's language. Also activates automatically when your code imports `anthropic` or `@anthropic-ai\/sdk`. Run `migrate` to update existing Claude API code to a newer model. Run `upgrade` to move your project's Anthropic SDK dependency across a major version, currently the Python `anthropic` package from 0.x to 1.x. Run `managed-agents-onboard` for a walkthrough that creates a new Managed Agent. Run `prompt-audit` to flag instructions written for older models in your prompts, skills, and tool descriptions and propose fixes as a diff. Run `cost-optimize` to profile where your project's Claude API spend goes and propose savings from options such as prompt caching, trimming unneeded input and output tokens, batch processing, effort, and model choice, one change at a time. Run `build-eval` to build an eval set for your Claude-powered app, and `hillclimb` to iteratively improve the app against an existing eval. The `prompt-audit` subcommand requires Claude Code v2.1.221 or later, `upgrade` requires v2.1.236 or later, `cost-optimize` requires v2.1.247 or later, and `build-eval` and `hillclimb` require v2.1.259 or later","description_source":"docs","described_by":{"doc":"claude-code\/commands","title":"Commands"},"presence":{"first_seen":null,"removed_in":null,"in_current_build":false,"newest_mined":"2.1.308","builds":0,"mined_builds":149,"first_cited":null},"aliases":[],"entries":[{"version":"2.1.305","anchor":"tengu-kind-dewdrop-gate-added-to-a-gate-list-velvet-gannet","heading":"Changes to some features that are switched off by default","line":"A new remote switch was added to a list, and a condition behind another switched-off feature now needs an extra test","released_at":"2026-10-20 19:29:36","reason":"found in this entry's text"},{"version":"2.1.305","anchor":"managed-agents-id-guard-for-ant-commands","heading":"The \/claude-api command check now accepts some local IDs","line":"The `\/claude-api` check still blocks `ant` commands with staging, Vertex or Bedrock IDs, and now accepts strict local-server IDs","released_at":"2026-10-20 19:29:36","reason":"found in this entry's text, named in this entry"},{"version":"2.1.304","anchor":"claude-api-managed-agents-secure-guard-on-ant-commands","heading":"\/claude-api now blocks some ant commands before they run","line":"The \/claude-api skill now blocks `ant` commands with certain IDs and managed-agents-secure commands changed from the guide","released_at":"2026-10-19 19:47:15","reason":"found in this entry's text, named in this entry"},{"version":"2.1.301","anchor":"tip-for-multiple-sessions-is-hidden-in-some-cases-the-claud","heading":"The tip about \/color and \/rename is skipped in more cases","line":"The tip suggesting \/color and \/rename for telling sessions apart is now hidden in some extra cases","released_at":"2026-10-15 14:34:23","reason":"found in this entry's text, named in this entry"},{"version":"2.1.290","anchor":"bundled-claude-api-skill-adds-managed-agents-quickstarts","heading":"Built-in claude-api skill gains managed-agents guides and quickstarts","line":"The claude-api skill that ships with Claude Code now includes managed-agents reference docs, nine quickstart templates and an onboarding flow","released_at":"2026-10-05 18:12:44","reason":"found in this entry's text"},{"version":"2.1.239","anchor":"python-sdk-upgrade-guide-rewritten-against-the-shipped-anthr","heading":"Python SDK upgrade guide rewritten against the shipped anthropic 1.0.0 migration notes","line":"The \/claude-api Python upgrade guide now matches the released 1.0.0 SDK built on httpx2.","released_at":"2026-08-21 17:18:54","reason":"named in this entry, found in this entry's text"},{"version":"2.1.236","anchor":"bundled-guide-for-upgrading-the-anthropic-python-sdk-to-1-x","heading":"Bundled guide for upgrading the anthropic Python SDK to 1.x","line":"A bundled guide walks your project through upgrading the anthropic Python SDK to 1.x.","released_at":"2026-08-19 18:45:14","reason":"named in this entry, found in this entry's text"},{"version":"2.1.221","anchor":"migrate-now-ends-with-a-prompt-audit-and-a-todo-note-ships-i","heading":"migrate now ends with a prompt audit, and a TODO note ships inside the prompt","line":"The migrate command now finishes by auditing your prompts and tool descriptions for stale wording.","released_at":"2026-08-03 22:16:25","reason":"named in this entry"},{"version":"2.1.221","anchor":"claude-api-skill-gains-a-prompt-audit-subcommand","heading":"claude-api skill gains a prompt-audit subcommand","line":"You can run \/claude-api prompt-audit to scan prompts and tool descriptions for outdated patterns and get a diff.","released_at":"2026-08-03 22:16:25","reason":"named in this entry, found in this entry's text"},{"version":"2.1.219","anchor":"bundled-claude-api-skill-docs-rewritten-around-opus-5","heading":"Bundled Claude API skill docs rewritten around Opus 5","line":"The bundled Claude API skill docs now target the new Opus, covering thinking defaults, fallbacks and fast mode.","released_at":"2026-07-24 16:11:49","reason":"named in this entry"}],"entries_total":11,"docs":[{"source":"claude-code","path":"commands","title":"Commands","documented":true},{"source":"api","path":"about-claude\/models\/migration-guide","title":"Or, for the model with the same capabilities and no access approval requirement:","documented":false},{"source":"api","path":"about-claude\/models\/optimizing-for-cost-and-intelligence","title":"optimizing-for-cost-and-intelligence","documented":false},{"source":"api","path":"agents-and-tools\/agent-skills\/claude-api-skill","title":"claude-api-skill","documented":false},{"source":"api","path":"agents-and-tools\/agent-skills\/overview","title":"PDF Processing","documented":false},{"source":"api","path":"build-with-claude\/claude-in-amazon-bedrock","title":"claude-in-amazon-bedrock","documented":false},{"source":"api","path":"build-with-claude\/claude-in-microsoft-foundry","title":"claude-in-microsoft-foundry","documented":false},{"source":"api","path":"build-with-claude\/claude-on-vertex-ai","title":"claude-on-vertex-ai","documented":false},{"source":"api","path":"build-with-claude\/claude-platform-on-aws","title":"claude-platform-on-aws","documented":false},{"source":"api","path":"build-with-claude\/preserved-thinking","title":"preserved-thinking","documented":false}],"docs_total":13,"gates":[],"related":[{"name":"\/claude-test","slug":"claude-test","description":"New built-in 'Claude Test' plugin runs plain-language specs against your local dev server in a real browser and reports PASS\/FAIL"}],"url":"https:\/\/changelogs.core-directive.com\/reference\/slash\/claude-api","family_url":"https:\/\/changelogs.core-directive.com\/reference\/slash.json"}