Borrowing it
Nothing to install: this file belongs to bijutharakan/multi-agent-squad. 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/bijutharakan/multi-agent-squad/main/.claude/commands/start-feature.mdgit clone --depth 1 https://github.com/bijutharakan/multi-agent-squadWrote 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/bijutharakan/multi-agent-squad/start-feature)<a href="https://agentmods.dev/commands/bijutharakan/multi-agent-squad/start-feature"><img src="https://agentmods.dev/badge/commands/bijutharakan/multi-agent-squad/start-feature/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/bijutharakan/multi-agent-squad/start-feature"><img src="https://agentmods.dev/badge/commands/bijutharakan/multi-agent-squad/start-feature.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 | $0.00023 | $0.00584 |
| Opus 5.5 | $0.00009 | $0.00234 |
| Sonnet 5.5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
start-feature 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start Feature Command
This command initiates a new feature development with full Multi-Agent Squad orchestration.
What This Command Does
- Gathers Requirements - Prompts for feature details
- Creates GitHub Issue - Tracks the feature (if integrated)
- Analyzes Impact - Determines which repositories are affected
- Creates Worktrees - Sets up isolated development environments
- Assigns Agents - Deploys appropriate specialists
- Begins Development - Kicks off implementation
Usage
Simply say:
/start-feature- "Start a new feature"
- "I want to add [feature description]"
Interactive Process
I'll ask you:
- Feature Name (kebab-case, e.g., "user-authentication")
- Feature Description (what should it do?)
- User Story (as a user, I want...)
- Affected Components (or I'll analyze)
- Priority (high/medium/low)
- Target Deadline (optional)
Example Flow
You: /start-feature
Me: Let's start a new feature! What would you like to call it?
You: payment-integration
Me: Great! Please describe what this feature should do.
You: Add Stripe payment processing for subscriptions
Me: I'll analyze which repositories this affects...
- Backend: API endpoints for payment processing
- Frontend: Payment forms and subscription management
- Database: Schema updates for subscriptions
Creating worktrees:
✓ backend/feature-payment-integration
✓ frontend/feature-payment-integration
Assigning agents:
- Backend Developer Agent → Payment API
- Frontend Developer Agent → Payment UI
- Database Expert → Schema updates
GitHub Issue #47 created: "Feature: Payment Integration"
Ready to begin development! The PM Agent will now create detailed requirements.
What Happens Next
- Product Manager Agent creates detailed requirements
- Solution Architect designs the implementation
- Developers work in their assigned worktrees
- Progress is tracked in GitHub
- PRs are created when ready
- Review by senior engineers
- Merge and cleanup when complete
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 · 90 lines · 23 tokens per session scan A ea41977dd803
start-feature is a command published in the GitHub repository bijutharakan/multi-agent-squad (88 stars, last pushed 1y ago), licensed MIT. It adds 23 tokens to every session and 584 once invoked, about $0.0001 per session on Opus 5.5. 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.
start-feature compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| start-featurebijutharakan/multi-agent-squad | Command | 88 | 1y ago | MIT | A | 23 | Claude Code |
| merge-conflict-analysisrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |
| release-notesOpenHands/extensions | Command | 176 | yesterday | MIT | A | 44 | Claude Code |
| commitechoVic/blade-code | Command | 181 | 24d ago | MIT | A | 8 | Claude Code |
| repo-audittractorjuice/arc-kit | Command | 2.3k | 2d ago | none | A | 29 | Claude Code |
| propsmill/infrahub-mcp | Command | 10 | yesterday | Apache-2.0 | A | 18 | Claude Code |
| codex-reviewoalders/kitchen-sink | Command | 5 | 3d ago | MIT | A | 41 | Claude Code |