new-work-new-branch

new-work-new-branch is a cursor rule for Cursor from David405/harness-kit. It costs 188 tokens per session, scanned A, original, Apache-2.0.

A workflow rule requiring every feature or fix to begin on a dedicated Git branch, which is an isolated line of project history. The developer must confirm the branch name before creating or switching to it.

In plain words
What is it for?
Use it whenever starting feature or bug-fix work. It guides branch naming, confirmation, creation, and the rule that commits require explicit approval.
Why use it?
It keeps unrelated work separate and prevents changes from being made directly on the default branch. It also leaves branch creation under human control.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it whenever starting feature or bug-fix work. It guides branch naming, confirmation, creation, and the rule that commits require explicit approval.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/david405/harness-kit/new-work-new-branch
Install

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.

Clone the repo
git clone --depth 1 https://github.com/David405/harness-kit

Made for: Cursor.

Wrote 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.

agentmods badge for new-work-new-branch

README.md
[![agentmods](https://agentmods.dev/badge/rules/david405/harness-kit/new-work-new-branch/github.svg)](https://agentmods.dev/rules/david405/harness-kit/new-work-new-branch)
Your own site
<a href="https://agentmods.dev/rules/david405/harness-kit/new-work-new-branch"><img src="https://agentmods.dev/badge/rules/david405/harness-kit/new-work-new-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.

agentmods 80×15 button for new-work-new-branch

Your own site · 80×15
<a href="https://agentmods.dev/rules/david405/harness-kit/new-work-new-branch"><img src="https://agentmods.dev/badge/rules/david405/harness-kit/new-work-new-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 188 This file is loaded in full into every session.
When invoked 188 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00188 $0.00188
Opus 5.5 $0.00075 $0.00075
Sonnet 5.5 $0.00038 $0.00038
Haiku 4.5 $0.00019 $0.00019

Measured 2mo ago against content hash 2eb092b44160, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

new-work-new-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 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.

rules/new-work-new-branch.mdc · 20 lines

What it actually says

New work goes on a new branch

Never implement on the default branch.

  1. Check the current branch and whether this work belongs there.
  2. Propose a branch name and base.
  3. Stop and ask: "Confirm feature branch <name> (yes, or give another name)." Do not create or switch branches until the human answers.
  4. Do not pile unrelated work onto an in-flight branch.
  5. After approval, create the branch. Do not commit until the human explicitly asks (e.g. "commit", "commit and push").
  6. Tell the human which branch is active when execution starts.

Name from the contract or ticket id when one exists; otherwise short kebab-case scope.

Changes

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.

  1. 2mo ago First seen · 20 lines · 188 tokens per session scan A 2eb092b44160

Subscribe to this mod's changes

new-work-new-branch is a cursor rule published in the GitHub repository David405/harness-kit (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 188 tokens to every session, about $0.0008 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 2026-08-31.