Skip to content
agentscamp

Commands

Reusable slash commands that automate repeatable workflows in Claude Code.

Slash commands are reusable prompts you invoke with /name. Each is a Markdown file you drop into ~/.claude/commands — automate repeatable workflows like reviews, commits, and refactors with a single keystroke.

28 results

Command

Explain Error

Diagnose an error message or stack trace and propose a fix.

/explain-error<error message or stack trace>
Command

DB Migrate

Generate and apply a database migration the safe way — using the project's migration tool, with expand-contract discipline for breaking changes, lock-free DDL, and a reversible up/down.

/db-migrate<the schema change to make, or a path to a pending migration to review>
Command

Scaffold a pgvector Schema & HNSW Index

Scaffold a production-ready pgvector schema and HNSW index for a corpus — matching the project's migration tooling, distance metric, and embedding dimensions.

/scaffold-pgvector-schema<table/corpus name and embedding dimensions, or a description of the data>
Command

Add Docstrings

Add or improve docstrings for the public API of a file or symbol.

/add-docstrings<file or symbol>
Command

Explain Code

Explain what the given code does, in clear prose with a short summary.

/explain-code[file or symbol]
Command

Update README

Update the README to reflect the current scripts, structure, and features of the repo.

/update-readme[section or focus]
Command

Commit

Stage changes and write a Conventional Commits message describing them.

/commit
Command

Create PR

Push the current branch and open a GitHub pull request with a generated title and body.

/create-pr[base branch or notes]
Command

Sync Branch

Fetch and rebase the current branch onto its base, resolving conflicts and verifying the build.

/sync-branch[base branch]
Command

Profile Postgres Queries

Profile a Postgres workload to find the queries actually costing you — rank by total time with pg_stat_statements, EXPLAIN the worst offenders, and recommend the highest-leverage fix.

/profile-postgres-queries<database/connection details, a slow endpoint, or a description of the workload>
Command

Set Perf Budget

Define and enforce a cost and latency budget for an LLM feature or endpoint — set p95/p99 latency and cost-per-request ceilings, instrument to measure them against real traffic, and wire a check that fails when the budget is breached.

/set-perf-budget<the LLM endpoint/feature to budget, plus any target numbers (e.g. 'chat API, p95 < 2s, < $0.02/req')>
Command

Breakdown Task

Decompose a task into an ordered checklist of small, verifiable steps.

/breakdown-task<task>
Command

Plan Feature

Explore the codebase and produce an implementation plan for a feature.

/plan-feature<feature description>
Command

Extract Function

Extract a code region into a well-named function and update the call site.

/extract-function<file:lines or description>
Command

Refactor

Refactor the target for readability and structure without changing behavior.

/refactor[file or function]
Command

Benchmark Rerankers

Measure whether adding a reranker actually improves retrieval, by scoring reranked vs. un-reranked results on a labeled query set.

/benchmark-rerankers<path to eval set / retrieval results, or a description of the pipeline>
Command

Find Bug

Investigate a reported symptom, form hypotheses, and locate the root cause.

/find-bug[symptom]
Command

Red Team LLM

Red-team an LLM app or agent for prompt injection, jailbreaks, and data leakage — probe the real attack surface (input, RAG, tools, system prompt) with adversarial inputs and report what got through and how to fix it.

/red-team-llm<the app/endpoint/agent to test, or a description of its inputs, tools, and data>
Command

Review PR

Review a pull request for correctness, security, and style, and summarize findings.

/review-pr[PR number]
Command

Security Scan

Scan the current diff or given paths for security vulnerabilities.

/security-scan[paths]
Command

Add Human Approval Step

Scaffold a human-in-the-loop approval gate into an agent so it pauses before a consequential action and resumes after approval.

/add-human-approval<the action/tool to gate, or the agent file>
Command

Add a Streaming LLM Endpoint

Scaffold a token-streaming LLM endpoint — server-side streaming plus the client handler — so responses render incrementally instead of after a long wait.

/add-streaming-endpoint<the route/feature to stream, or the framework>
Command

New Component

Scaffold a new UI component matching the project conventions.

/new-component<ComponentName> [props]
Command

Scaffold a vLLM Serving Config

Scaffold a vLLM serving config for a model on a target GPU — pick precision/quantization and parallelism to fit, set batching and context length, and expose an OpenAI-compatible server.

/scaffold-vllm-config<model + target GPU(s) and VRAM, or a description of the serving workload>
Command

Fix Failing Test

Diagnose and fix a failing test by finding the real root cause.

/fix-failing-test[test name or path]
Command

Run Evals

Run the project's LLM evaluation suite (DeepEval, promptfoo, or RAGAS) and report scores against thresholds before a merge.

/run-evals<eval suite path / config, or the feature to evaluate>
Command

Write Tests

Generate tests covering the happy path and edge cases for the given target.

/write-tests[file or function]
Command

Add MCP Server

Add an MCP server to the current project the safe way — pick the transport and scope, wire secrets through env vars, vet provenance, and verify the connection before trusting it.

/add-mcp-server<server name + launch command or URL, or a description of the server to add>

Frequently asked questions

What is a Claude Code slash command?
A slash command is a reusable prompt saved as a Markdown file and invoked with /name in Claude Code. It expands into instructions Claude follows, optionally using arguments via $ARGUMENTS.
How do I install a slash command?
Save the command to ~/.claude/commands/<name>.md for all your projects, or .claude/commands/<name>.md inside a single project. Then type /<name> in Claude Code to run it.
Can commands take arguments?
Yes. Reference $ARGUMENTS in the command body and anything you type after the command name is substituted in, so one command can handle many inputs.
Are these commands free?
Yes. Every slash command on AgentsCamp is free to copy, download, and install, with no signup required.
How is a command different from an agent?
A slash command is a prompt you trigger manually with /name in your main conversation. An agent is a subagent with its own context window that Claude can delegate to automatically. Commands are quick and explicit; agents are autonomous and isolated.