bootstrap

One command to full AgentOps product layer. Sets up GOALS.md, PRODUCT.md, README.md, .agents/ structure, and hooks. Progressive -- fills gaps only. Triggers: "bootstrap", "setup agentops", "initialize repo", "full setup".

244 stars

Best use case

bootstrap is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

One command to full AgentOps product layer. Sets up GOALS.md, PRODUCT.md, README.md, .agents/ structure, and hooks. Progressive -- fills gaps only. Triggers: "bootstrap", "setup agentops", "initialize repo", "full setup".

Teams using bootstrap should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/bootstrap/SKILL.md --create-dirs "https://raw.githubusercontent.com/boshu2/agentops/main/skills-codex/bootstrap/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/bootstrap/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How bootstrap Compares

Feature / AgentbootstrapStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

One command to full AgentOps product layer. Sets up GOALS.md, PRODUCT.md, README.md, .agents/ structure, and hooks. Progressive -- fills gaps only. Triggers: "bootstrap", "setup agentops", "initialize repo", "full setup".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# $bootstrap (Codex Native)

> **Quick Ref:** One command to set up the full AgentOps product layer. Progressive -- bare repos get everything, existing repos fill gaps only.

**YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.**

## Quick Start

```
$bootstrap
```

That is it. One command. Every step below is idempotent -- existing artifacts are never overwritten.

## Flags

| Flag | Effect |
|------|--------|
| `--dry-run` | Report what would be created without doing anything |
| `--force` | Recreate artifacts even if they already exist |

## Execution Steps

### Step 0: Detect Repo State

```bash
git rev-parse --is-inside-work-tree >/dev/null 2>&1 || { echo "NOT_A_GIT_REPO"; exit 1; }
HAS_GOALS=$([[ -f GOALS.md ]] && echo true || echo false)
HAS_PRODUCT=$([[ -f PRODUCT.md ]] && echo true || echo false)
HAS_README=$([[ -f README.md ]] && echo true || echo false)
HAS_AGENTS=$([[ -d .agents ]] && echo true || echo false)
HAS_HOOKS=$(grep -rq "agentops" .git/hooks/ 2>/dev/null && echo true || echo false)
HAS_AO=$(command -v ao >/dev/null && echo true || echo false)
```

Classify the repo:

| State | Condition |
|-------|-----------|
| **bare** | No GOALS.md, no PRODUCT.md, no .agents/ |
| **partial** | Some artifacts present, some missing |
| **complete** | All artifacts present |

If `--dry-run` is set: report the state and what would be created, then stop. Do not proceed to Steps 1-6.

If the repo is **complete** and `--force` is not set: report "Repo is fully bootstrapped. Nothing to do." and stop.

### Step 1: GOALS.md

If `HAS_GOALS` is false (or `--force` is set):

Run the goals initialization inline. Prompt the user for project purpose, key metrics, and initial directives. Write GOALS.md with:
- Mission statement
- Initial directives (3-5 recommended)
- Fitness thresholds

```bash
# Check if ao CLI is available for goals init
if command -v ao >/dev/null 2>&1; then
  ao goals init
else
  # Generate GOALS.md inline from user input
  echo "# Goals" > GOALS.md
  echo "" >> GOALS.md
  echo "## Mission" >> GOALS.md
  echo "<prompt user for mission>" >> GOALS.md
fi
```

If `HAS_GOALS` is true and `--force` is not set: skip. Report "GOALS.md exists -- skipped."

### Step 2: PRODUCT.md

If `HAS_PRODUCT` is false (or `--force` is set):

Run the product definition inline. Interview the user about mission, personas, value props, and competitive landscape. Write PRODUCT.md with filled-in sections.

If `HAS_PRODUCT` is true and `--force` is not set: skip. Report "PRODUCT.md exists -- skipped."

### Step 3: README.md

If `HAS_README` is false (or `--force` is set) AND PRODUCT.md now exists:

Generate README.md from PRODUCT.md content. Include: project name, description, installation, usage, contributing section.

If `HAS_README` is true and `--force` is not set: skip. Report "README.md exists -- skipped."

If PRODUCT.md does not exist (Step 2 was skipped or failed): skip. Report "README.md skipped -- PRODUCT.md required first."

### Step 4: .agents/ Structure

If `HAS_AGENTS` is false (or `--force` is set):

Create the directory structure:

```bash
mkdir -p .agents/learnings .agents/council .agents/research .agents/plans .agents/rpi
```

Create `.agents/AGENTS.md` if it does not exist:

```markdown
# Agent Knowledge Store

This directory contains accumulated knowledge from agent sessions.

## Structure

| Directory | Purpose |
|-----------|---------|
| `learnings/` | Extracted lessons and patterns |
| `council/` | Council validation artifacts |
| `research/` | Research phase outputs |
| `plans/` | Implementation plans |
| `rpi/` | RPI execution packets and phase logs |

## Usage

Knowledge is automatically managed by the AgentOps flywheel:
- `$inject` surfaces relevant prior knowledge at session start
- `$post-mortem` extracts and processes new learnings
- `$compile` runs maintenance (mine, grow, defrag)
```

If `HAS_AGENTS` is true and `--force` is not set: skip. Report ".agents/ exists -- skipped."

### Step 5: Hook Activation

If `HAS_AO` is true AND `HAS_HOOKS` is false (or `--force` is set):

```bash
ao init --hooks
```

If `HAS_AO` is false: skip. Report "Hooks skipped -- ao CLI not installed. Run: brew tap boshu2/agentops https://github.com/boshu2/homebrew-agentops && brew install agentops"

If `HAS_HOOKS` is true and `--force` is not set: skip. Report "Hooks already configured -- skipped."

### Step 6: Report

Output a summary table:

```
Bootstrap complete.

| Artifact      | Status  |
|---------------|---------|
| GOALS.md      | created / skipped / failed |
| PRODUCT.md    | created / skipped / failed |
| README.md     | created / skipped / failed |
| .agents/      | created / skipped / failed |
| Hooks         | activated / skipped / failed |

Repo is now AgentOps-ready. Next: $rpi "your first goal"
```

## Troubleshooting

| Problem | Cause | Solution |
|---------|-------|---------|
| "Not a git repo" | No .git directory | Run `git init` first |
| Goals step fails | No project context | Provide a one-line project description when prompted |
| Product step fails | No goals defined | Run goals init manually first, then re-run `$bootstrap` |
| Hooks not activating | ao CLI not installed | Install: `brew tap boshu2/agentops https://github.com/boshu2/homebrew-agentops && brew install agentops` |
| Want to start over | Existing artifacts blocking | Use `--force` to recreate all artifacts |

## See Also

- `../goals/SKILL.md` -- Fitness specification and directive management
- `../product/SKILL.md` -- Product definition generation
- `../readme/SKILL.md` -- README generation
- `../quickstart/SKILL.md` -- New user onboarding (lighter than bootstrap)

Related Skills

vibe

244
from boshu2/agentops

Comprehensive code validation. Runs complexity analysis then multi-model council. Answer: Is this code ready to ship? Triggers: "vibe", "validate code", "check code", "review code", "code quality", "is this ready".

validation

244
from boshu2/agentops

Full validation phase orchestrator. Vibe + post-mortem + retro + forge. Reviews implementation quality, extracts learnings, feeds the knowledge flywheel. Triggers: "validation", "validate", "validate work", "review and learn", "validation phase", "post-implementation review".

update

244
from boshu2/agentops

Reinstall all AgentOps skills globally from the latest source. Triggers: "update skills", "reinstall skills", "sync skills".

trace

244
from boshu2/agentops

Trace design decisions and concepts through session history, handoffs, and git. Triggers: "trace decision", "how did we decide", "where did this come from", "design provenance", "decision history".

test

244
from boshu2/agentops

Test generation, coverage analysis, and TDD workflow. Triggers: "test", "generate tests", "test coverage", "write tests", "tdd", "add tests", "test strategy", "missing tests", "coverage gaps".

status

244
from boshu2/agentops

Single-screen dashboard showing current work, recent validations, flywheel health, and suggested next action. Triggers: "status", "dashboard", "what am I working on", "where was I".

standards

244
from boshu2/agentops

Language-specific coding standards and validation rules. Provides Python, Go, Rust, TypeScript, Shell, YAML, JSON, and Markdown standards. Auto-loaded by $vibe, $implement, $doc, $bug-hunt, $complexity based on file types.

shared

244
from boshu2/agentops

Shared reference documents for multi-agent skills (not directly invocable)

security

244
from boshu2/agentops

Continuous repository security scanning and release gating. Triggers: "security scan", "security audit", "pre-release security", "run scanners", "check vulnerabilities".

security-suite

244
from boshu2/agentops

Composable security suite for binary and prompt-surface assurance, static analysis, dynamic tracing, repo-native redteam scans, contract capture, baseline drift, and policy gating. Triggers: "binary security", "reverse engineer binary", "black-box binary test", "behavioral trace", "baseline diff", "prompt redteam", "security suite".

scenario

244
from boshu2/agentops

Author and manage holdout scenarios for behavioral validation. Scenarios are stored in .agents/holdout/ where implementing agents cannot see them. Triggers: "$scenario", "holdout", "behavioral scenario", "create scenario", "list scenarios".

scaffold

244
from boshu2/agentops

Project scaffolding, component generation, and boilerplate setup. Triggers: "scaffold", "new project", "init project", "create project", "generate component", "setup project", "starter", "boilerplate".