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.
npx agentmods add rules/first-fluke/fullstack-starter/branching-strategygit clone --depth 1 https://github.com/first-fluke/fullstack-starterWrote 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/rules/first-fluke/fullstack-starter/branching-strategy)<a href="https://agentmods.dev/rules/first-fluke/fullstack-starter/branching-strategy"><img src="https://agentmods.dev/badge/rules/first-fluke/fullstack-starter/branching-strategy.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.02261 |
| Opus 5 | $0.00005 | $0.01130 |
| Sonnet 5 | $0.00002 | $0.00452 |
| Haiku 4.5 | $0.00001 | $0.00226 |
Grade A, and why
branching-strategy 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 today.
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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Branching Strategy
Overview
GitFlow-inspired branching strategy for this project. Solo development omits the develop branch.
Branch Types
| Branch | Purpose | Optional |
|---|---|---|
main |
Production codebase | No |
develop |
Integration for team development | Yes (solo: skip) |
feature/* |
New features | No |
fix/* |
Bug fixes | No |
hotfix/* |
Urgent production fixes | No |
release/* |
Release preparation | Yes |
Branch Naming Rules
-
Features:
feature/<descriptive-name>- Examples:
feature/user-authentication,feature/dark-mode
- Examples:
-
Fixes:
fix/<descriptive-name>- Examples:
fix/login-error,fix/memory-leak
- Examples:
-
Hotfixes:
hotfix/<descriptive-name>- Examples:
hotfix/security-patch,hotfix/critical-bug
- Examples:
-
Releases:
release/<version>- Examples:
release/v1.0.0,release/v2.1.0
- Examples:
Workflow
Creating Feature Branch
# From main (solo or team)
git checkout main
git pull origin main
git checkout -b feature/your-feature-name
# OR from develop (team only)
git checkout develop
git pull origin develop
git checkout -b feature/your-feature-name
Creating Hotfix Branch
# Always from main (production)
git checkout main
git pull origin main
git checkout -b hotfix/urgent-fix-description
Merging Hotfix
# 1. Merge to main and tag release
git checkout main
git merge hotfix/urgent-fix-description
git tag -a v1.0.2 -m "Hotfix version 1.0.2"
git push origin v1.0.2
# 2. Back-merge to develop (if using team workflow)
git checkout develop
git merge hotfix/urgent-fix-description
# 3. Delete hotfix branch
git branch -d hotfix/urgent-fix-description
Creating Release Branch
Note: Release branch is optional. For most cases, merge develop directly to main with a tag.
When to use release branches:
- Finalizing release features
- Preparing for production deployment
- Testing release candidate before deployment
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.
- today First seen · 355 lines · 9 tokens per session scan A aa6de21dd1c9
branching-strategy is a cursor rule published in the GitHub repository first-fluke/fullstack-starter (222 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 2,261 once invoked, about $0.0000 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 cursor rules, from other repositories
avoid_source_deduplication
name: avoid-source-deduplication description: Preserve unique source entries in search results to maintain proper citation tracking globs: ['/connectorservice.py', '/searchservice.py'] alwaysApply: true.
consistent_container_image_sources
name: consistent-container-image-sources description: Maintain consistent image sources in Docker compose files using authorized registries globs: ['/docker-compose.yml', '/docker-compose..yml'] alwaysApply: true.
no_env_files_in_repo
name: no-env-files-in-repo description: Prevent committing environment and configuration files containing sensitive credentials globs: ['/.env', '/.env.', '/config/.yml', '/config/.yaml'] alwaysApply: true.
require_unique_id_props
name: require-unique-id-props description: Ensure unique key props are provided when mapping arrays to React elements globs: ['/.tsx', '/.jsx'] alwaysApply: true.
cursorrules
use pnpm as default package manager.
cursorrules
Cursor rule "cursorrules" from sseshachala/conductai, covering conductguard policy and agent booster — context-efficient reads.