Skip to content
Back to skills

Docko Repo

ASecurity

Repository onboarding and working conventions for the docko monorepo. Use when an agent needs to understand the repo layout, choose the right docs or commands, plan a change, or verify work without crossing the core, cli, adapters, docs, and tests boundaries.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 22, 2026
ai-agentsapidocumentation

Works with

  • cli
  • api

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 22, 2026

npx -y skills add 4riel/docko --skill docko-repo --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Docko Repo?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Docko Repo
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/4riel-docko-repo/badge)](https://www.skillsdirectory.com/skills/4riel-docko-repo)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: docko-repo
description: Repository onboarding and working conventions for the docko monorepo. Use when an agent needs to understand the repo layout, choose the right docs or commands, plan a change, or verify work without crossing the core, cli, adapters, docs, and tests boundaries.
---

# docko Repo

How this monorepo is laid out and which surface owns which change. Use it when planning work
anywhere in the repo.

## Read first

- `AGENTS.md`
- `README.md`
- `docs/INDEX.md`
- `docs/repo-structure.md`
- `docs/development.md`
- For Codex-specific wording, verify against official OpenAI docs before editing repo guidance.

## Navigate by surface

- `packages/core`: protocol semantics, registry and session state, claims, delegation, authorization
- `packages/cli`: public command surface and JSON output shaping
- `packages/adapters/claude-code`: only implemented runtime adapter today
- `schemas/`: canonical JSON Schema
- `tests/`: unit, e2e, and adapter coverage
- `examples/`: copy-pastable runtime and workspace examples that should match the shipped behavior

## Work pattern

- Start from docs, then confirm behavior in source.
- Keep changes inside the narrowest owning package or doc surface.
- Treat `registry.json` as canonical and `registry.md` as generated.
- If the task becomes protocol-heavy, read `docs/protocol.md`, `docs/architecture.md`, `docs/cli-reference.md`, and use `docko-protocol`.
- If the task becomes adapter-heavy, read `docs/adapter-spec.md`, `docs/claude-code.md`, and use `docko-adapters`.
- If the task becomes documentation-heavy, read `docs/development.md` and use `docko-docs`.
- Keep Claude adapter docs grounded in `packages/adapters/claude-code/src/index.ts`, `packages/adapters/claude-code/templates/`, and `tests/claude-code-adapter.test.mjs`.
- Keep Codex guidance grounded in official OpenAI docs and describe it as manual guidance unless this repo gains a real Codex adapter package.

## Verify

- `pnpm build`
- `pnpm check`
- `pnpm test`
- Call out missing tooling or unrun verification explicitly.

Files in this skill

  • SKILL.md2 KB
  • agents/openai.yaml240 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.