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/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/new-feature-branch)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/new-feature-branch"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/new-feature-branch/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/atretyak1985/swarmery/new-feature-branch"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/new-feature-branch.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 | $0.00027 | $0.01140 |
| Opus 5 | $0.00014 | $0.00570 |
| Sonnet 5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
new-feature-branch 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 8d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/new-feature-branch — start work on fresh main
Automates the per-issue branch workflow that every operator task in this project starts with, so the four-step recipe becomes one command.
Usage
/new-feature-branch <slug-describing-the-work>
Examples:
/new-feature-branch fix/rollback-drift-check/new-feature-branch feat/maps-api-key-secret/new-feature-branch docs/runtime-maps-env-usage/new-feature-branch chore/check-chart-sync-helper
What it does
git checkout main— switch to the main branch.git pull origin main— fast-forward local main.git checkout -b <slug>— create feature branch.git push -u origin <slug>— push empty branch so it can be protected in GitHub before substantive commits land.
Total: four commands replaced by one invocation.
Branch naming convention
Prefix describes intent:
| Prefix | Use for |
|---|---|
feat/ |
New functionality |
fix/ |
Bug fix |
docs/ |
Docs-only changes |
chore/ |
Tooling / dev-experience / maintenance |
refactor/ |
Code structure changes, no behaviour change |
test/ |
Test-only changes |
Slug after prefix: dash-separated, lowercase, short but meaningful.
Implementation
#!/usr/bin/env bash
set -Eeuo pipefail
slug="${1:?usage: new-feature-branch <prefix/slug>}"
git checkout main
git pull --ff-only origin main
git checkout -b "$slug"
git push -u origin "$slug"
echo "✓ Branch '$slug' created at main HEAD and pushed. Protect it in GitHub before substantive commits if desired."
Prerequisites
- You are inside the target git repo's working tree.
- Working tree is clean (no uncommitted changes) OR your changes are stashed.
originremote is configured.
Related
- The staging health command (if the project ships one, e.g.
/<envAlias>-health) — first diagnostic after starting any deploy-related work - Commit-message convention: see
skills/git-commit/
How to use
What it does
Starting a branch the right way takes four commands, and skipping one leaves you branching off a stale main or with an unpushed branch that nobody can protect. This command does all four for you: it switches to main, fast-forwards it, cuts your new branch, and pushes it empty so branch protection can be applied before any real commit lands.
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.
- 8d ago First seen · 129 lines · 27 tokens per session scan A 454e0b1036cf
new-feature-branch is a command published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 1,140 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other commands, from other repositories
quick-push
Git add all, commit with Claude, and push to current/new feature branch.
changelog
Generate a structured changelog from recent git commits, categorized by change type.
commit-push-pr
An automated Git workflow that checks a project, synchronizes documentation, commits changes, and can create or merge a GitHub pull request. A pull request is a request for teammates to review and add changes to a shared codebase.
devkit.github.create-pr
Creates a GitHub pull request with branch creation, commits, and detailed description. Use when you need to submit changes for review.
pre-commit-check
Tu es un assistant de qualité code. Tu dois effectuer toutes les vérifications nécessaires AVANT de créer un commit, pour garantir que le code respecte les standards du projet.
hatch3r-pr-resolve
Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.