Borrowing it
Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/.claude/commands/agent-engagesubagents.mdgit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWrote 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/gpt-cmdr/ras-commander/agent-engagesubagents)<a href="https://agentmods.dev/commands/gpt-cmdr/ras-commander/agent-engagesubagents"><img src="https://agentmods.dev/badge/commands/gpt-cmdr/ras-commander/agent-engagesubagents/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/gpt-cmdr/ras-commander/agent-engagesubagents"><img src="https://agentmods.dev/badge/commands/gpt-cmdr/ras-commander/agent-engagesubagents.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 | $0.00846 |
| Opus 5 | $0.00000 | $0.00423 |
| Sonnet 5 | $0.00000 | $0.00169 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
agent-engagesubagents 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search through your agents and skills and make a detailed plan to execute the user's query. Use the agents to save context and use shared documents in agent_tasks as a form of memory and passive coordination layer.
First, list the proposed agents for the user's review and approval. Then, ultrathink and write a detailed execution plan that can be expanded and progress summaries noted by multiple agents, as well as a place to provide references to external files that document their individual work product and findings.
Subagent Engagement Protocol
1. Plan and List Proposed Agents
Before dispatching, present the user with:
- Which subagents will be used
- What each subagent will do
- Expected output files and locations
- Estimated complexity (Haiku / Sonnet / Opus)
Wait for user approval before proceeding.
2. Model Selection Guidance
| Complexity | Model | Use When |
|---|---|---|
| Simple, focused, fast | Haiku | Documentation lookup, file reads, scanning, summarization |
| Moderate, multi-step | Sonnet | Analysis, code generation, multi-file coordination |
| Complex, deep reasoning | Opus | Architecture decisions, cross-domain synthesis, hard problems |
Default to Sonnet unless there is clear reason to go up or down.
3. Context Handoff Pattern (Critical)
Always pass context via file paths, never raw text.
Correct pattern:
- Pass relative file paths in the subagent prompt
- Subagent reads those files for context
- Subagent writes output to .claude/outputs/{subagent}/{date}-{task}.md
- Subagent returns the output file path (not raw text)
Wrong pattern:
- Embedding large text blobs directly in the prompt
- Subagent returning large text instead of writing a file
Path format: Always use relative paths from repository root. CORRECT: agent_tasks/.agent/STATE.md CORRECT: .claude/outputs/hdf-analyst/analysis.md WRONG: C:/GH/ras-commander/agent_tasks/.agent/STATE.md (absolute)
4. Execution Plan File
Before dispatching agents, write an execution plan to agent_tasks:
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.
- 9d ago First seen · 98 lines · 0 tokens per session scan A aeced9c3dffb
agent-engagesubagents is a command published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 846 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.