Get StartedSAFE
A framework-agnostic, git-native standard for defining AI agents
Overview
A framework-agnostic, git-native standard for defining AI agents
799d6d0ad18cOBSERVED · 2026-10-07Install
Commands as the repository documents them. They are shown, not run.
npm install -g @open-gitagent/opengap
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: get-started description: "Guides installation of gitagent and creation of first agent with scaffolding, configuration, and validation. Use when the user is new to gitagent, asks how to get started, wants to install gitagent, set up their first agent, or says 'how do I start?'" license: MIT metadata: author: gitagent version: "1.0.0" category: onboarding --- # Get Started with gitagent ## When to Use When a user is new to gitagent, wants to set up their first agent, or asks "how do I start?" ## Instructions ### Installation ```bash npm install -g @open-gitagent/opengap opengap --version ``` ### Create Your First Agent Walk the user through these steps: 1. **Scaffold** — Pick a template: ```bash # Minimal (2 files) opengap init --template minimal --dir ./my-agent # Standard (with skills, tools, knowledge) opengap init --template standard --dir ./my-agent # Full (compliance, hooks, memory, workflows) opengap init --template full --dir ./my-agent ``` 2. **Edit** — Customize `agent.yaml` (name, description, model) and `SOUL.md` (identity, personality) 3. **Validate** — Check your work: ```bash opengap validate -d ./my-agent ``` 4. **Run** — Launch with Claude: ```bash opengap run -d ./my-agent ``` 5. **Share** — Push to git and anyone can run it: ```bash cd my-agent && git init && git add . && git commit -m "Initial agent" # Push to GitHub, then: opengap run -r https://github.com/you/my-agent ``` ### Minimum Required Files - `agent.yaml` — name, version, description (required) - `SOUL.md` — agent identity (required) - Everything else is optional
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
799d6d0ad18cfull audit observations/trust-audit/skill/open-gitagent__get-started.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 799d6d0ad18c | SAFE | B | 89 | first audit |
Questions
What does the Get Started skill do?
A framework-agnostic, git-native standard for defining AI agents
Is Get Started safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Get Started access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (799d6d0ad18c), read on 2026-10-07. The repository is watched, and a new audit runs when it changes — this is the first audit.