claude-cli
Skill2 starsChanged 8 months agoMITView on GitHub
Expert control of the `claude` CLI (Claude Code). Use when running Claude Code interactively or non-interactively, managing sessions, configuring MCP servers, managing plugins, handling authentication, or piping prompts through claude for scripting.
- Reads credentials
7 other projects use a version of this.
Adopted by
Most recently taken up by
- Acnologia7021/codex-skillstheir own version, first seen Nov 8, 2026
- tzoofu/skillstheir own version, first seen Nov 8, 2026
- choughton/feature-design-prompt-templatestheir own version, first seen Nov 8, 2026
- samirpatil2000/skillstheir own version, first seen Nov 1, 2026
- namos2502/CortexLinktheir own version, first seen May 4, 2026
- nguyenvanhuy0612/claude-skillstheir own version, first seen Apr 21, 2026
Other versions7 projects use a version of this.
Word for word · 1
- julweber/ai_agent_skills★ 2100% same
Edited · 0
None found.
Wrote their own version · 6
- samirpatil2000/skills★ 17same name
- choughton/feature-design-prompt-templates★ 1same name
- tzoofu/skills★ 1same name
- Acnologia7021/codex-skills★ 0same name
- namos2502/CortexLink★ 0same name
- nguyenvanhuy0612/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository51 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-agent-skills-assistantSkill
- ansibleSkill
- artificial-analysisSkill
- cavemanSkill
- code-doctorSkill
- code-summarizerSkill
- codex-cliSkill
- concourse-ciSkill
- dev-brainstormingSkill
- docker-cliSkill
- file-organizerSkill
- frontend-web-developerSkill
- github-actions-cicdSkill
- github-cliSkill
- gitlab-ci-cdSkill
- grill-meSkill
- gtd-assistantSkill
- herdr-cliSkill
- hf-cliSkill
- karpathy-guidelinesSkill
- kestraSkill
- list-large-filesSkill
- list-most-intensive-processesSkill
- llama-cppSkill
- llm-wikiSkill
- mermaidSkill
- morning-ritualSkill
- obsidian-masterSkill
- obsidian-open-loops-collectorSkill
- opencode-agent-creatorSkill
- opencode-cliSkill
- pi-cliSkill
- pi-subagents-masterSkill
- planka-development-flowSkill
- plnk-cliSkill
- ponytailSkill
- product-prd-brainstormingSkill
- python-api-developerSkill
- ralph-prd-converterSkill
- ralph-prd-generatorSkill
- release-managementSkill
- rest-testsuite-skillSkill
- skill-loaderSkill
- design-taste-frontendSkill
- terraformSkill
- tmux-coderSkill
- tmux-specialistSkill
- trello-cliSkill
- tts-conversationSkill
- uvSkill
The file
Files
Claude CLI
claude starts an interactive session by default. Use -p/--print for non-interactive/scripted usage.
Key Runtime Flags
| Flag | Description |
-p, --print | Non-interactive: print response and exit (pipe-friendly) |
-c, --continue | Continue most recent conversation in current directory |
-r, --resume [id] | Resume session by ID, or open interactive picker |
--fork-session | Create new session ID when resuming (use with -r/-c) |
--model <model> | Model alias (sonnet, opus) or full name (claude-sonnet-4-6) |
--effort <level> | Effort level: low, medium, high |
--session-id <uuid> | Use specific UUID for this conversation |
--system-prompt <prompt> | Override system prompt |
--append-system-prompt <prompt> | Append to default system prompt |
-w, --worktree [name] | Create git worktree for this session |
--tmux | Create tmux session for worktree (requires --worktree) |
--ide | Auto-connect to IDE if exactly one is available |
--chrome / --no-chrome | Enable/disable Chrome integration |
Output & Format (with --print)
claude -p "prompt" # text output
claude -p --output-format json "prompt" # single JSON result
claude -p --output-format stream-json "prompt" # streaming JSON
claude -p --input-format stream-json # streaming JSON input
claude -p --include-partial-messages "prompt" # include partial chunks
claude -p --max-budget-usd 0.50 "prompt" # cap spend
claude -p --fallback-model sonnet "prompt" # fallback if overloaded
claude -p --no-session-persistence "prompt" # don't save sessionTool Control
--allowedTools "Bash(git:*) Edit Read" # whitelist tools
--disallowedTools "Bash" # blacklist tools
--tools "Bash,Edit,Read" # exact set from built-ins
--tools "" # disable ALL tools
--permission-mode bypassPermissions # skip all prompts
--dangerously-skip-permissions # bypass all checks
--allow-dangerously-skip-permissions # make bypass available as optionPermission modes: acceptEdits, bypassPermissions, default, dontAsk, plan
MCP Configuration
--mcp-config server.json # load MCP servers from JSON file
--strict-mcp-config # only use --mcp-config servers
--mcp-debug # [DEPRECATED] use --debug insteadAgents
--agent <name> # override agent for session
--agents '{"reviewer":{"description":"...","prompt":"..."}}' # define inline agentsDebug & Settings
-d, --debug [filter] # debug mode, optional category filter
--debug-file <path> # write debug logs to file
--verbose # verbose output
--setting-sources user,project,local # which config sources to load
--settings <file-or-json> # load additional settings
--disable-slash-commands # disable all skills
--plugin-dir <path> # load plugins from dir (session only)
--betas <betas...> # beta headers (API key users only)
--file file_id:relative_path # download file resource at startup
--from-pr [number/url] # resume session linked to a PR
--add-dir <directories...> # extra dirs for tool access
--json-schema <schema> # JSON schema for structured output
--replay-user-messages # re-emit user messages on stdoutSubcommands
claude auth
claude auth login [--email <email>] [--sso] # sign in (SSO flag forces SSO flow)
claude auth logout # log out
claude auth status [--json|--text] # show auth statusclaude mcp — MCP Server Management
# Add stdio server
claude mcp add my-server -- npx my-mcp-server
claude mcp add -e API_KEY=xxx my-server -- npx my-mcp-server
# Add HTTP server
claude mcp add --transport http sentry https://mcp.sentry.dev/mcp
claude mcp add --transport http corridor https://app.corridor.dev/api/mcp \
--header "Authorization: Bearer TOKEN"
# OAuth HTTP server
claude mcp add --transport http --client-id <id> --client-secret my-server <url>
# Scope: local (default), user, or project
claude mcp add -s project my-server -- my-command
# Other operations
claude mcp add-json my-server '{"command":"npx","args":["server"]}'
claude mcp add-from-claude-desktop [-s <scope>] # import from Claude Desktop (Mac/WSL)
claude mcp list
claude mcp get <name>
claude mcp remove <name> [-s <scope>]
claude mcp reset-project-choices # reset approved/rejected project MCP servers
claude mcp serve [-d] [--verbose] # start Claude Code as an MCP serverclaude plugin — Plugin Management
claude plugin install <plugin>[@marketplace] [-s user|project|local]
claude plugin uninstall <plugin> [-s <scope>]
claude plugin list [--json] [--available]
claude plugin enable <plugin> [-s <scope>]
claude plugin disable [plugin] [-s <scope>] [-a] # -a disables all
claude plugin update <plugin> [-s user|project|local|managed]
claude plugin validate <path> # validate plugin manifest
# Marketplace management
claude plugin marketplace add <url|path|github-repo>
claude plugin marketplace list [--json]
claude plugin marketplace remove <name>
claude plugin marketplace update [name] # all if no name givenclaude agents
claude agents [--setting-sources <sources>] # list configured agentsSystem Commands
claude install [target] [--force] # install native build (stable/latest/version)
claude update # check for updates and install
claude doctor # check auto-updater health
claude setup-token # set up long-lived auth token (requires subscription)Common Workflows
# Non-interactive one-shot
claude -p "Explain this file" < README.md
# Continue last session
claude -c
# Resume specific session
claude -r abc-123-uuid
# Fork a session (branch it)
claude -r abc-123-uuid --fork-session
# Use specific model
claude --model opus -p "Complex task"
# Add MCP server scoped to project
claude mcp add -s project github -- npx @modelcontextprotocol/server-github
# Pipe JSON output for scripting
claude -p --output-format json "list files" | jq '.result'
# Allow all tools, skip prompts (sandboxed CI use)
claude -p --dangerously-skip-permissions "run tests"
# Budget-capped automation
claude -p --max-budget-usd 1.00 --output-format json "analyze codebase"
# Stream output in real-time
claude -p --output-format stream-json --include-partial-messages "write code"Environment Variables
ANTHROPIC_API_KEY— API key for authenticationMCP_CLIENT_SECRET— OAuth client secret for MCP HTTP servers (alternative to--client-secretprompt)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

