Approve Swarm — Development skill for Claude Code
Record human approval of a swarm plan.
How to install Approve Swarm
Installs to ~/.claude/commands/friedbotstudio-baseline-approve-swarm.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/friedbotstudio/baseline/HEAD/.claude/commands/approve-swarm.md -o ~/.claude/commands/friedbotstudio-baseline-approve-swarm.md Restart Claude Code, or start a new session, for it to be picked up.
What Approve Swarm does
description: Record human approval of a swarm plan. swarm-dispatch will not run until this approval token exists. Must be user-invoked — Claude cannot approve. argument-hint: ".json; .md is stripped if present>" allowed-tools: Read, Bash(date:*), Write disable-model-invocation: true
The user has reviewed the swarm plan referenced by `$ARGUMENTS` and approved it for dispatch.
How this works structurally: when the user typed `/approve-swarm
Alternatives in Development
- Maestro Learn — User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions 530 ★
- Pi Reserved Keybindings — Extensions cannot override these shortcuts — they are silently skipped by registerShortcut() 526 ★
- Taskmaster — Stop hook for Claude Code that keeps the agent working until all plans and user requests are 100% complete 494 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ldd Explain
Explain why LDD just invoked the skill(s) it invoked — cite the trigger phrase from the user's message that ma
Dd Approve
Check whether a version- and scope-bound approval record currently authorizes a gated action, and state exactl
Reviewzy
File user-facing copy for human approval, then apply it in a later session
Swarm Iosm
Parallel Subagent Orchestration Engine for Claude Code implementing the IOSM methodology. Continuous dispatch
Research Swarm
Dispatch 5-10 parallel research sub-agents on a new domain before writing code. Mandatory for new APIs, librar
Auto Swarm Nth
Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100
Related Agents
Approval Gate
HumanLayer-inspired approval gate. Enforces human-in-the-loop for HIGH-stakes operations. Classifies actions b
Deploy Guard
Pre-deploy validation gate. HUMAN-INVOKED ONLY. Project-scope permission rule Agent(deploy-guard) is DENIED in
Scene Builder
Builds one episodes/ /scenes/scene-NN.html GSAP scene from an approved plan.md scene card and its narration fi