A Team — A Complete Engineering Team in One Folder v1.1.0
Not a marketplace of agents you configure. A pre-configured, pre-enforced engineering team of 25 specialists — with a lead orchestrator, hard quality gates, and a Pipeline Auditor that verifies work was actually done, not just reported. Drop one folder into any project and it's operational from the first keystroke. Works on Claude Code, Codex CLI, Cursor, and OpenCode.
Born from the community. A Team was built by studying, using, and needing to personalise several excellent open-source agent projects. The architecture combines the best patterns from each into a single, portable baseline. See Acknowledgments for the projects that made this possible.
→ Visual overview & live demo
Domain packs — install any alongside A Team:
- builder-ai — LLM engineering quality (evals, RAG, prompt versioning, safety)
- builder-design — AI UI design (states, streaming, accessibility, tokens)
- builder-product — Product quality gates (PRD, metrics, research synthesis, AI validation)
- builder-growth — Growth & messaging (positioning, copy, experiments, retention)
What It Does
A Team turns any AI coding assistant into a structured, self-enforcing engineering team. Instead of one general-purpose model trying to do everything, you get:
- 25 specialist agents, each with a defined scope, model tier, and tool set
- 18 workflow skills that gate what can happen and when
- A lead orchestrator that manages daily task flow, dispatch, and state
- Hard enforcement hooks that inject mandatory checks at session start and after every file edit
- A pipeline auditor that verifies agents actually ran required checks — not just claimed they did
The infrastructure is stateless by design. Every agent derives its context from files, not memory. Sessions can be interrupted and resumed without drift.
Installation
Pick the method that fits your setup. All methods install the same files into your project directory.
Option A — One-liner (recommended)
Mac / Linux / WSL:
bash <(curl -fsSL https://raw.githubusercontent.com/RBraga01/a-team/main/install.sh)
Windows PowerShell:
irm https://raw.githubusercontent.com/RBraga01/a-team/main/install.ps1 | iex
To install into a specific directory, pass the path as an argument:
bash <(curl -fsSL https://raw.githubusercontent.com/RBraga01/a-team/main/install.sh) /path/to/project
Option B — GitHub CLI
# Clone the repo (shallow, only latest commit)
gh repo clone RBraga01/a-team -- --depth 1
# Copy the infrastructure into your project
cp -r a-team/.claude your-project/
cp -r a-team/skills your-project/
cp -r a-team/hooks your-project/
cp -r a-team/templates your-project/
cp a-team/INIT_TEMPLATE.md your-project/INIT.md
# Clean up
rm -rf a-team
Option C — Git (no GitHub CLI)
# Sparse clone — downloads only the necessary directories, not the full repo
git clone --filter=blob:none --sparse --depth 1 \
https://github.com/RBraga01/a-team.git
cd a-team
git sparse-checkout set .claude skills hooks templates INIT_TEMPLATE.md
# Copy into your project
cp -r .claude skills hooks templates ../your-project/
cp INIT_TEMPLATE.md ../your-project/INIT.md
cd .. && rm -rf a-team
Windows (PowerShell equivalent):
git clone --filter=blob:none --sparse --depth 1 `
https://github.com/RBraga01/a-team.git
cd a-team
git sparse-checkout set .claude skills hooks templates INIT_TEMPLATE.md
Copy-Item -Recurse .claude,skills,hooks,templates ..\your-project\
Copy-Item INIT_TEMPLATE.md ..\your-project\INIT.md
cd .. ; Remove-Item a-team -Recurse -Force
Option D — Download ZIP (no git required)
- Go to github.com/RBraga01/a-team
- Click Code → Download ZIP
- Extract and copy
.claude/, skills/, hooks/, templates/ into your project root
- Copy
INIT_TEMPLATE.md as INIT.md
Adding A Team to an Existing Project
If the project is already in progress, use cp -rn (no-clobber) when copying the folders so your existing files are not overwritten:
cp -rn a-team/.claude ./
cp -rn a-team/skills ./
cp -rn a-team/hooks ./
cp -rn a-team/templates ./
cp a-team/INIT_TEMPLATE.md ./INIT.md
Then fill out INIT.md to describe what already exists — languages, frameworks, current test coverage, known technical debt. The orchestrator uses this to prune irrelevant agents; accuracy here matters more than on a greenfield project.
