team-setup

Overview

team-setup is an interactive skill that guides you through setting up the team AI directives. It presents four modes, explains each option, confirms your choice, and executes the setup.

It is invoked in two ways:

• User-invoked (/team-setup) — anytime, to configure or check a project.
• Model-invoked by team-boot — automatically at session start when a project has no .adlc/init-options.json configuration (self-install), so an unconfigured project wires itself without the user knowing the command.

The skill is non-destructive: it never overwrites existing files or directories. If the target path already contains a configured team AI directives, it detects this and offers the "Already configured" mode instead.

When to Use

• Starting a new team from scratch and need a neutral team AI directives scaffold to fill in later.
• Your team already has a directives repo on GitHub and you want to clone it locally.
• You have a local team AI directives directory already (e.g., from a previous project) and want to wire it up.
• You're unsure whether the team AI directives is already configured and want a quick check.
• When the project isn't yet wired to a team AI directives (no .adlc/init-options.json team_ai_directives field).
• Automatically via team-boot when it detects an unconfigured project at session start (self-install).

Decline Handling (when model-invoked by team-boot)

When team-boot invokes this skill because the project is unconfigured, the user may choose not to set up team AI directives right now. Handle decline explicitly to avoid a re-prompt loop:

• If the user declines at mode selection, do not run any mode. Exit cleanly and tell team-boot the user declined.
• Offer a persistent opt-out: "Don't ask again for this project?" On yes (build mode only), write .adlc/init-options.json with team_ai_directives: null:

  echo '{"team_ai_directives": null}' > ".adlc/init-options.json"
  

  This marker makes team-boot skip setup silently on every future prompt.
• In plan/read-only mode, a persistent opt-out cannot be written — the decline is session-scoped only; tell team-boot to defer.
• Never force a mode; the setup is user-consented at every step.

Core Process

Goal

Set up a team AI directives using one of four modes.

Security: Input Validation (all modes)

Before executing any mode, validate every user-supplied value (paths, URLs, team names). These values are interpolated into shell commands; unvalidated input is a command-injection vector.

• Paths ({DEST}, {ABSOLUTE_PATH}): reject if they contain any of `, $, ;, |, &, (, ), <, >, newline, or backslash. Resolve to an absolute path with realpath/Resolve-Path before use.
• Team name: must match ^[A-Za-z0-9 ._-]+$. Reject anything else.
• Clone URL (Mode 1): must start with https://. Reject file://, ssh://, and any non-https scheme unless the user explicitly confirms the risk. Cloning runs no code from the repo, but the cloned content is read by agents later — only clone repositories you trust.

If any value fails validation, report which value and why, and re-ask. Never interpolate a user value into a Python/eval source string — pass it through the environment (see Mode 2).

Mode 1: Clone from GitHub

Clone an existing team-ai-directives repository from GitHub.

Explore:

1. Ask the user for the GitHub repository URL (default: https://github.com/tikalk/agentic-sdlc-team-ai-directives)
2. Validate the URL starts with https:// (reject file://, ssh://, and other schemes — see Input Validation). Only clone repositories you trust; the cloned content is read by agents later.
3. Ask where to clone it (default: ./team-ai-directives)
4. Check that the destination does not already exist

Present: Show the user:

• Source URL
• Destination path
• Estimated size (from remote repo info if available)

Confirm:

Clone team-ai-directives from {URL} to {DEST}?
[Y/n]

Write/Execute:

git clone "{URL}" "{DEST}"

After clone, verify the team AI directives structure exists:

• {DEST}/context_modules/constitution.md
• {DEST}/context_modules/rules/
• {DEST}/context_modules/personas/
• {DEST}/context_modules/examples/
• {DEST}/CDR.md
• {DEST}/.skills.json

Mode 2: Point to Existing Local Path

Wire an existing local team-ai-directives directory into the project.

Explore:

1. Ask the user for the path to their existing team AI directives directory
2. Validate the path exists
3. Validate the team AI directives structure (same checks as Mode 1 post-clone)
4. If validation fails, explain what's missing and ask the user to fix it or choose a different mode

Present: Show the user:

• Resolved absolute path
• Validation results (which required files/dirs exist and which are missing)

Confirm:

Use existing team-ai-directives at {ABSOLUTE_PATH}?
[Y/n]

Write/Execute: Update the project's .adlc/init-options.json to set the team_ai_directives field to the resolved path. Uses jq for safe JSON manipulation — never interpolate user input into shell source.

# Resolve to an absolute path and validate (see Input Validation)
ABSOLUTE_PATH="$(realpath "$USER_PATH")"

# Write config using jq (merge into existing or create new)
if [ -f ".adlc/init-options.json" ]; then
  jq --arg p "$ABSOLUTE_PATH" '. + {team_ai_directives: $p}' ".adlc/init-options.json" > ".adlc/init-options.json.tmp" && mv ".adlc/init-options.json.tmp" ".adlc/init-options.json"
else
  jq -n --arg p "$ABSOLUTE_PATH" '{team_ai_directives: $p}' > ".adlc/init-options.json"
fi

Mode 3: Scaffold New Empty team AI directives

Create a fresh, neutral team AI directives at a specified path.

Explore:

1. Ask the user where to create the team AI directives (default: ./team-ai-directives)
2. Ask for the team name
3. Check the destination does not already exist or is empty

Present: Show the user the 10 files that will be created:

#	File	Purpose
1	README.md	Getting started documentation
2	AGENTS.md	Agent instructions (loading order, rules, skills)
3	CDR.md	Derived CDR index stub (auto-generated by /team-repair)
4	.skills.json	Empty skills manifest (schema v2.0.0: default/external/blocked/policy)
5	.mcp.json.example	Empty MCP servers config example
6	context_modules/constitution.md	Placeholder constitution (OKF v0.2 frontmatter) — fill via /team-constitution
7	context_modules/index.md	OKF v0.2 root index (okf_version: "0.2") linking sub-directories
8	context_modules/log.md	OKF §9 aggregate update log
9	context_modules/rules/index.md	OKF §8 progressive disclosure (rules)
10	context_modules/rules/log.md	OKF §9 rules audit trail
11	context_modules/rules/.gitkeep	Rules directory placeholder
12	context_modules/personas/index.md	OKF §8 progressive disclosure (personas)
13	context_modules/personas/log.md	OKF §9 personas audit trail
14	context_modules/personas/.gitkeep	Personas directory placeholder
15	context_modules/examples/index.md	OKF §8 progressive disclosure (examples)
16	context_modules/examples/log.md	OKF §9 examples audit trail
17	context_modules/examples/.gitkeep	Examples directory placeholder
18	skills/.gitkeep	Skills directory placeholder

Confirm:

Scaffold empty team-ai-directives at {DEST} with team name "{TEAM_NAME}"?
[Y/n]

Write/Execute:

Create directory structure:

mkdir -p "{DEST}/context_modules/rules"
mkdir -p "{DEST}/context_modules/personas"
mkdir -p "{DEST}/context_modules/examples"
mkdir -p "{DEST}/skills"

Create {DEST}/README.md:

# {TEAM_NAME} Team AI Directives

Team AI directives repository for {TEAM_NAME}.

## Getting Started

1. Wire this directives repository into a project:

/team-setup

Choose "Point to existing local path" and select this directory.

2. Add context modules to `context_modules/` (rules, personas, examples).

3. Add skills to `skills/` and register them in `.skills.json`.

4. Update `CDR.md` as context modules are approved.

See [ADLC Team Skills](https://github.com/tikalk/adlc-team-skills) for full documentation.

Create {DEST}/AGENTS.md:

# Agent Instructions

## Structure

- `context_modules/constitution.md` — Team constitution
- `context_modules/rules/` — Team rules and workflows
- `context_modules/personas/` — Team personas
- `context_modules/examples/` — Team examples
- `skills/` — Team skills
- `CDR.md` — Context Directive Records

## Loading Order

1. Load constitution.md first
2. Load relevant rules for the current task
3. Load relevant personas for the current task
4. Load relevant examples for the current task

## Using Skills

Skills are located in the `skills/` directory. Browse available skills using `team-skills` and install them as needed.

## CDR.md

CDR.md is a derived flat table, auto-generated by `/team-repair` from per-directory `index.md` files. It is used by `team-boot` for system prompt injection. Do not edit manually — run `/team-repair` to regenerate.

Create {DEST}/CDR.md:

# Context Directive Records (Derived Index)

> ⚠️ Auto-generated by `/team-repair`. Do not edit manually.
> Source of truth: `context_modules/*/index.md` + module frontmatter.
> Decision lifecycle (Accepted/Rejected) lives in project `.adlc/drafts/cdr/`.

## CDR Index

| ID | Path | Type | Description | Generated | Verified | Age | Status |
|----|------|------|-------------|-----------|----------|-----|--------|

**Stats**: 0 entries | Last Updated: {TODAY}

Create {DEST}/.skills.json:

{
  "version": "2.0.0",
  "source": "team-ai-directives",
  "description": "Team skills manifest. The `default` list contains skill names that are auto-installed during project setup. The `external` map contains on-demand skills fetched by URL. The `blocked` list contains skills that must never be installed.",
  "default": [],
  "external": {},
  "blocked": [],
  "policy": {
    "auto_install_default": true,
    "enforce_blocked": true,
    "allow_project_override": true
  }
}

Create {DEST}/.mcp.json.example:

{
  "mcpServers": {}
}

Create {DEST}/context_modules/constitution.md:

---
type: Constitution
title: "{TEAM_NAME} Constitution"
description: "Team-wide principles and governance"
resource: ./context_modules/constitution.md
tags: [constitution]
generated: { by: agent:team-setup, at: {TODAY}T00:00:00Z }
id: constitution
cdr_ref: null
created: {TODAY}
verified:
  - { by: agent:team-setup, at: {TODAY}T00:00:00Z }
status: stable
stale_after: 180d
---

# {TEAM_NAME} Constitution

No team-wide principles defined yet. Add principles as they are established.

Create OKF v0.2-compliant index.md and log.md files for progressive disclosure:

Create {DEST}/context_modules/index.md:

---
okf_version: "0.2"
---

# Context Modules

* [Rules](rules/index.md) - Team rules and workflows
* [Personas](personas/index.md) - Team personas
* [Examples](examples/index.md) - Team examples

Create {DEST}/context_modules/log.md:

# Context Modules Update Log

Create {DEST}/context_modules/rules/index.md:

# Rules

No rules defined yet. Use `/levelup-specify` to create rules via CDRs.

Create {DEST}/context_modules/rules/log.md:

# Rules Update Log

Create {DEST}/context_modules/personas/index.md:

# Personas

No personas defined yet. Use `/levelup-specify` to create personas via CDRs.

Create {DEST}/context_modules/personas/log.md:

# Personas Update Log

Create {DEST}/context_modules/examples/index.md:

# Examples

No examples defined yet. Use `/levelup-specify` to create examples via CDRs.

Create {DEST}/context_modules/examples/log.md:

# Examples Update Log

Create gitkeep files:

touch "{DEST}/context_modules/rules/.gitkeep"
touch "{DEST}/context_modules/personas/.gitkeep"
touch "{DEST}/context_modules/examples/.gitkeep"
touch "{DEST}/skills/.gitkeep"

Initialize git (required for /levelup-publish branch/commit/PR flow):

cd "{DEST}" && git init && git add -A && git commit -m "Initial team-ai-directives scaffold"

Follow-up: The scaffolded context_modules/constitution.md is a placeholder ("No team-wide principles defined yet"). Tell the user:

Scaffold complete. Run /team-constitution next to establish your team's
principles interactively — it detects the placeholder and walks you through
creating the real constitution.

After scaffold, run the post-setup configuration (same as Mode 4 below).

Mode 4: Already Configured

The team AI directives is already configured. Verify and report status.

Explore:

1. Check .adlc/init-options.json for team_ai_directives field
2. If found, resolve the path and validate the team AI directives structure
3. Check TEAM_AI_DIRECTIVES env var as fallback
4. Check default path team-ai-directives as final fallback

Present: Show the user the resolved team AI directives path and validation results.

Write/Execute: No writes needed — the team AI directives is already configured. Then run the MCP config install (see Post-Setup Configuration step 4): merge .mcp.json servers into the project's config if not already present.

Mode Selection Flow

1. Explore: Present the user with four options:

   How would you like to set up team-ai-directives?
   
   1) Clone from GitHub — Clone an existing repository
   2) Point to existing local path — Use a team AI directives you already have
   3) Scaffold new empty team AI directives — Create a fresh neutral team AI directives
   4) Already configured — Check existing configuration
   

2. Present: For the chosen mode, explain what will happen and show details.

3. Confirm: Ask the user to confirm before executing.

4. Write/Execute: Perform the setup for the chosen mode.

Post-Setup Configuration

After any mode completes successfully, update the project configuration:

1. Write team_ai_directives to .adlc/init-options.json
2. Verify the team AI directives is accessible by running a quick health check:
   • {TEAM_AI_DIRECTIVES}/context_modules/constitution.md exists
   • {TEAM_AI_DIRECTIVES}/.skills.json exists and is valid JSON
3. Inject the project-level AGENTS.md directive so agents auto-invoke team-boot at session start:

# Bash
bash "$(dirname "$0")/team-helpers.sh" --inject-agents "{PROJECT_ROOT}"

# PowerShell
pwsh "$(Split-Path $PSCommandPath -Parent)/team-helpers.ps1" -InjectAgents "{PROJECT_ROOT}"

This creates or updates the project's AGENTS.md with a managed section (between <!-- TEAM_AI_DIRECTIVES START --> and <!-- TEAM_AI_DIRECTIVES END --> markers) containing:

• Event-hook awareness: notes that team-boot runs automatically at session start via the event hook (for agents with event support), injecting a lean orientation into the first user message.
• Fallback invocation: "If the team AI directives context is NOT in your system prompt or first user message (agent without event support), invoke the team-boot skill before responding to any task or question."
• Unconfigured handling: "If team AI directives are unconfigured, invoke the team-setup skill."
• Team Context in Use contract: "Every response MUST include a Team Context in Use section before the task answer" — a 4-column table (ID | Name | Type | Relevance) listing genuinely matched CDRs/skills, followed by _Searched N CDR entries, M skills, J matched._

Without this section, an agent without event support has no session-start instruction to load team context, and the team AI directives repository remains invisible until manually loaded. The section is idempotent: re-running team-setup or team-repair updates the section in place without duplicating content.

4. Install MCP config: Read {TEAM_AI_DIRECTIVES}/.mcp.json if it exists, and merge its mcpServers configuration into the project's own .mcp.json or .opencode/mcp.json config. Report which servers were merged, and highlight any unresolved environment variables needed by the servers.

Common Rationalizations

Rationalization	Why it's wrong	What to do instead
"I'll just clone it manually."	Manual cloning skips the .adlc/init-options.json wiring, so agents won't find the team AI directives.	Use Mode 1 — it clones AND configures.
"I already have a team AI directives directory, I'll just use it."	The directory may be incomplete (missing required files) or not wired in config.	Use Mode 2 — it validates the structure and creates the config entry.
"I'll just create a few files by hand."	An incomplete scaffold breaks health checks and agent discovery.	Use Mode 3 — it creates all 10 required files with valid structure.
"I'm sure it's already configured."	The path may be stale, moved, or the env var may point to a deleted dir.	Use Mode 4 — it validates the existing configuration.
"Scaffolding without a team name is fine."	The team name is used in README.md — a blank name makes the team AI directives anonymous and harder to audit.	Always provide a team name in Mode 3.

Red Flags

• Cloning over an existing directory — Mode 1 refuses if the destination already exists to prevent overwrites.
• Pointing to a non-existent path — Mode 2 validates the path exists before proceeding.
• Scaffolding without required dirs being writable — Mode 3 creates directories with mkdir -p but will fail on permission errors; check permissions first.
• Skipping the team_ai_directives config write — without this field in init-options.json, agents cannot discover the team AI directives.
• Using a relative path in init-options.json — always resolve to an absolute path so the config is portable across working directories.
• Skipping git init in Mode 3 — a scaffolded team AI directives without git cannot be used by /levelup-publish (branch/commit/PR flow). Mode 3 runs git init automatically; if you skip it, run git init manually before /levelup-publish.
• Skipping the project-level AGENTS.md injection — without the <!-- TEAM_AI_DIRECTIVES START --> managed section in the project's AGENTS.md, agents without event support have no session-start instruction to load team context. The .adlc/init-options.json config alone is insufficient — it tells skills where the team AI directives is, but nothing tells the agent to check. (For agents with event support, the session-start hook injects the orientation regardless, but AGENTS.md remains the fallback and the source of the Team Context in Use output contract.)
• Interpolating user input into Python/shell source strings — pass paths through the environment (os.environ) instead; string interpolation of $ABSOLUTE_PATH into a Python one-liner is a command-injection vector.
• Cloning a non-https:// URL in Mode 1 — reject file:///ssh:///other schemes; cloned content is read by agents later, so only clone trusted repos.
• Skipping the MCP config install — .mcp.json servers stay unconfigured; the project won't have access to team-declared MCP servers.
• Accepting shell metacharacters in paths or team names — validate before interpolating into mkdir/git commit/heredocs (see Input Validation).
• Treating user decline as an error — declining setup is a valid outcome; exit cleanly, tell team-boot the user declined, and offer the team_ai_directives: null opt-out marker (build mode only).
• Writing the opt-out marker in plan/read-only mode — a persistent opt-out requires a write; in plan mode the decline is session-scoped and setup defers instead.

Verification

• The team AI directives directory exists at the configured path.
• {TEAM_AI_DIRECTIVES}/context_modules/constitution.md exists.
• {TEAM_AI_DIRECTIVES}/context_modules/rules/ exists.
• {TEAM_AI_DIRECTIVES}/context_modules/personas/ exists.
• {TEAM_AI_DIRECTIVES}/context_modules/examples/ exists.
• {TEAM_AI_DIRECTIVES}/CDR.md exists.
• {TEAM_AI_DIRECTIVES}/.skills.json exists and is valid JSON.
• .adlc/init-options.json contains a team_ai_directives field with the absolute path.
• Project-level AGENTS.md exists and contains the <!-- TEAM_AI_DIRECTIVES START --> managed section with the event-hook awareness note, fallback team-boot invocation, and the Team Context in Use output contract.
• (Mode 3 only) git rev-parse --is-inside-work-tree succeeds inside {TEAM_AI_DIRECTIVES}.
• Running team-verify (Phase 0 of team-repair) passes all 7 checks.
• All user-supplied paths/URLs/team names passed Input Validation (no shell metacharacters; clone URL is https://).
• Mode 2 wrote team_ai_directives via the environment (no $ABSOLUTE_PATH interpolation into Python source).
• If {TEAM_AI_DIRECTIVES}/.mcp.json exists, any declared mcpServers were successfully merged into the project's config, and unresolved env vars were highlighted.
• (Model-invoked by team-boot) a user decline exited cleanly without running any mode; the persistent opt-out was offered, and team_ai_directives: null was written only in build mode.

Configuration

• TEAM_AI_DIRECTIVES — Path to the team AI directives (overrides .adlc/init-options.json).
• .adlc/init-options.json — Project-level config file with team_ai_directives field.
• Default fallback: team-ai-directives/ relative to project root.
• team-helpers.sh / team-helpers.ps1 — Shared scripts used for scaffolding and path resolution.

12-Factor Alignment

Factor XI (Directives as Code) — establishes a version-controlled team directives repository.