Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/hgahlot/claude-flowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/hgahlot/claude-flow/multi-execute)<a href="https://agentmods.dev/commands/hgahlot/claude-flow/multi-execute"><img src="https://agentmods.dev/badge/commands/hgahlot/claude-flow/multi-execute/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/hgahlot/claude-flow/multi-execute"><img src="https://agentmods.dev/badge/commands/hgahlot/claude-flow/multi-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00429 |
| Opus 5.5 | $0.00000 | $0.00172 |
| Sonnet 5.5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
multi-execute scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/multi-execute — Spawn Parallel Subagents for Independent Tasks
Coordinate parallel execution of independent tasks using subagents.
Instructions
- Identify parallelizable tasks — tasks with no shared state or file dependencies
- Scope each agent clearly — one focused goal per agent, explicit file boundaries
- Define integration point — what the orchestrator collects and how results merge
- Spawn agents — use the Agent tool with isolated prompts
- Collect and integrate — wait for all agents, then merge results
When to Use
- Multiple independent features that don't share files
- Parallel research (e.g., "research option A" + "research option B")
- Parallel test writing for independent modules
- Large refactors across independent subsystems
- Parallel security/performance analysis of different components
Prompt Template for Each Subagent
You are a focused subagent with ONE specific task.
Task: <exact task description>
Scope: Only work on these files: <file list>
Do NOT modify: <files to leave alone>
Success criteria:
- <specific verifiable outcome>
- Tests pass for your scope
When done, output a summary:
COMPLETED: <what was done>
FILES CHANGED: <list>
TESTS: <pass/fail count>
Orchestrator Checklist
Before spawning:
- Confirm tasks are truly independent (no shared file writes)
- Each agent has a clear, bounded scope
- Integration plan is defined before agents start
After collecting results:
- All agents reported COMPLETED
- No file conflicts in FILES CHANGED lists
- Run integrated test suite across all changes
- Run
/reviewon the combined diff
Rules
- Never give two agents write access to the same file
- Orchestrator context must stay minimal — delegate all heavy work
- If any agent fails, do not proceed with integration — debug first
- Always run the full test suite after integration, not just per-agent tests
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 57 lines · 0 tokens per session scan A 8235bd5ed8e1
multi-execute is a command published in the GitHub repository hgahlot/claude-flow (55 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 429 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
multi-execute compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| multi-executehgahlot/claude-flow | Command | 55 | 7mo ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |