parallel-agents · parcadei — Claude Code skill for parallel agents
The parallel-agents skill lays out a background-run and file-based workflow for coordinating agents. Use it to track parallel tasks without pulling each agent’s full response into context.
MIT ★ 3,951 updated 2026-01-26
npx skills add parcadei/Continuous-Claude-v3 --skill parallel-agents -a claude-codeWhat parallel-agents does
The skill recommends launching tasks with Task and run_in_background: true, then recording completion in files. For simple jobs, agents append a line to a shared status file. Research tasks get separate directories containing output.md, artifacts/, and status.txt. This keeps findings available while avoiding full responses from TaskOutput.
Use cat, wc -l, or tail -f to check progress. A batch can contain up to 15 agents, and the current batch should finish before another starts. Each agent needs a clear, self-contained prompt with the required context, since agents do not share memory. Launching more than 15 agents at once goes against the skill’s stated limit.
What it helps with
- launch several agent tasks in the background
- track agent completion in a shared status file
- keep research findings separate from completion markers
- give each agent an independent task and its needed context
Example prompts for the agent
- Split this work into parallel tasks and run the agents in the background; have each append its status to
.claude/cache/review-status.txt. - Ask agents to research separate options and save findings under
.claude/cache/agents/research/<agent-id>/output.md, with completion recorded instatus.txt. - Check the batch in
.claude/cache/provider-backfill-status.txtwithcatandwc -linstead of requesting full agent responses.
How to install parallel-agents
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill parallel-agents -a claude-code2Manually: put the files in place
~/.claude/skills/parallel-agents/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/parallel-agents/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill parallel-agents -a codex2Manually: put the files in place
.agents/skills/parallel-agents/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill parallel-agents -a cursor2Manually: put the files in place
.cursor/skills/parallel-agents/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install parcadei/Continuous-Claude-v3 .claude/skills/parallel-agents2Manually: put the files in place
.github/skills/parallel-agents/SKILL.md1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill parallel-agents -a gemini-cli2Platform CLI
gemini skills install https://github.com/parcadei/Continuous-Claude-v3 --path .claude/skills/parallel-agentsManually: put the files in place
.devin/skills/parallel-agents/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about parallel-agents
How do I install parallel-agents in Claude Code?
Run npx skills add parcadei/Continuous-Claude-v3 --skill parallel-agents -a claude-code. The skill file is at ~/.claude/skills/parallel-agents/SKILL.md.
What does parallel-agents do?
It describes a workflow for running agents in the background and tracking completion with status files. Detailed findings go into files rather than being fetched wholesale through TaskOutput.
What is the maximum batch size?
The skill sets a limit of 15 agents per parallel batch. Wait for that batch to finish before starting the next one.
Source text
SKILL.md · MIT
---
name: parallel-agents
description: Parallel Agent Orchestration
user-invocable: false
---
# Parallel Agent Orchestration
When launching multiple agents in parallel, follow this pattern to avoid context bloat.
## Core Principles
1. **No TaskOutput calls** - TaskOutput returns full agent output, bloating context
2. **Run in background** - Always use `run_in_background: true`
3. **File-based confirmation** - Agents write status to files, not return values
4. **Append, don't overwrite** - Multiple agents can write to same status file
## Output Patterns
### Simple Confirmation (parallel batch work)
For tasks where agents just need to confirm completion:
```bash
# Agent writes to shared status file
echo "COMPLETE: <task-name> - $(date)" >> .claude/cache/<batch-name>-status.txt
```
- Use `>>` to append (not `>` which overwrites)
- Include timestamp for ordering
- One line per agent completion
- Check with: `cat .claude/cache/<batch-name>-status.txt`
### Detailed Output (research/exploration)
For tasks requiring detailed findings:
```
.claude/cache/agents/<task-type>/<agent-id>/
├── output.md # Main findings
├── artifacts/ # Any generated files
└── status.txt # Completion confirmation
```
- Each agent gets own directory
- Full output preserved for later reading
- Status file still used for quick completion check
## Task Prompt Template
```markdown
# Task: <TASK_NAME>
## Your Mission
<clear objective>
## Output
When done, write confirmation:
\`\`\`bash
echo "COMPLETE: <identifier> - $(date)" >> .claude/cache/<batch>-status.txt
\`\`\`
Do NOT return large output. Complete work silently.
```
## Launching Pattern
```typescript
// Launch all in single message block (parallel)
Task({
description: "Task 1",
prompt: "...",
subagent_type: "general-purpose",
run_in_background: true
})
Task({
description: "Task 2",
prompt: "...",
subagent_type: "general-purpose",
run_in_background: true
})
// ... up to 15 parallel agents
```
## Monitoring
```bash
# Check completion status
cat .claude/cache/<batch>-status.txt
# Count completions
wc -l .claude/cache/<batch>-status.txt
# Watch for updates
tail -f .claude/cache/<batch>-status.txt
```
## Batch Size
- **Max 15 agents** per parallel batch
- Wait for batch to complete before launching next
- Use status file to track which completed
## DO
- Use `run_in_background: true` always
- Have agents write to status files
- Use append (`>>`) not overwrite (`>`)
- Give each agent clear, self-contained instructions
- Include all context in prompt (agents don't share memory)
## DON'T
- Call TaskOutput (bloats context)
- Return large outputs from agents
- Launch more than 15 at once
- Rely on agent return values for orchestration
## Example: Provider Backfill
```bash
# Status file
.claude/cache/provider-backfill-status.txt
# Each agent appends on completion
echo "COMPLETE: anthropic - Thu Jan 2 12:34:56 2025" >> .claude/cache/provider-backfill-status.txt
echo "COMPLETE: openai - Thu Jan 2 12:35:12 2025" >> .claude/cache/provider-backfill-status.txt
```
Check progress:
```bash
cat .claude/cache/provider-backfill-status.txt
# COMPLETE: anthropic - Thu Jan 2 12:34:56 2025
# COMPLETE: openai - Thu Jan 2 12:35:12 2025
```
© parcadei · MIT · parcadei/Continuous-Claude-v3
Similar skills
All skills for Agent setup: memory, context, orchestration →parallel-agents by other authors comes first.