create-agent SKILL.md skillA

create-agent from lijunzh/koda is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lijunzh/koda/create-agent@git:20261116.c35b66a

Pins git:20261116.c35b66a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lijunzh/koda
Path
koda-skills/skills/create-agent/SKILL.md
Versions recorded
1
Latest version
git:20261116.c35b66a, committed Nov 16, 2026
Size
8,797 bytes
Repository stars
15
License
MIT

Scaffold a new sub-agent JSON file (.koda/agents/<name>.json) with the correct schema, tool scoping, and trust mode.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Create Agent

You are scaffolding a new koda sub-agent. The goal: produce a working
`.koda/agents/<name>.json` (or `~/.config/koda/agents/<name>.json`) that
the user can immediately invoke via `InvokeAgent`.

## Principles

- **Read before writing.** Open `koda-core/agents/explore.json` (or
  `task.json`) to ground yourself in the
  canonical patterns before generating the file.
- **Declare `trust` explicitly.** This is the #1 footgun. Pre-#1250
  agents used `write_access` (now deprecated). Today every new agent
  must declare its natural `trust` mode — the kernel and approval
  matrix derive everything from it. Skipping `trust` falls back to
  legacy default-deny which silently strips Write/Edit and
  causes opaque "no such tool" failures.
- **Principle of least privilege.** Pick the lowest trust mode that
  works: `plan` for pure search/analysis, `safe` for write-capable
  workers, never `auto` (auto is reserved for the user-controlled
  top-level session).
- **One agent, one purpose.** A good `description` is a single sentence
  that lets the main agent know when to invoke it.

## Trust modes (the only knob you really need)
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_qgci6u2czu3374g5/196534cfe8dc6f5be9e8d8c48a12def76c3bed3bd03374a9e03f314112561a69.json

Then /plugin install create-agent@markdownregistry-qgci6u2czu3374g5 in Claude Code. It installs git:20261116.c35b66a, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add lijunzh/koda/create-agent@sha256:196534cfe8dc6f5b

The line at the top of this page pins the label git:20261116.c35b66a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qgci6u2czu3374g5.svg)](https://markdownregistry.com/a/art_qgci6u2czu3374g5)

0 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in lijunzh/koda/create-agent since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of create-agent from somewhere else? Ask it: where did my create-agent come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Nov 16, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261116.c35b66a latest2026-11-16 c35b66a 8,797 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8797 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

lijunzh/koda · 15 stars · license MIT · pushed 2026-11-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qgci6u2czu3374g5
GET https://markdownregistry.com/api/v1/resolve?ref=lijunzh/koda/create-agent
GET https://markdownregistry.com/api/v1/blob/196534cfe8dc6f5be9e8d8c48a12def76c3bed3bd03374a9e03f314112561a69

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from lijunzh/koda

AGENTS.md AGENTS.md file
lijunzh/koda · AGENTS.md
git:20261116.ffc4a26 · audit A · 15 stars
DESIGN.md DESIGN.md file
lijunzh/koda · DESIGN.md
git:20261115.602745f · audit A · 15 stars
code-review SKILL.md skill
lijunzh/koda · koda-skills/skills/code-review/SKILL.md · Senior code review — finds bugs, anti-patterns, and improvements
git:20261116.c35b66a · audit A · 15 stars
create-skill SKILL.md skill
lijunzh/koda · koda-skills/skills/create-skill/SKILL.md · Scaffold a new bundled skill (.koda/skills/<name>/SKILL.md) with correct frontmatter, tool scoping, and a clear…
git:20261116.c35b66a · audit A · 15 stars
debug SKILL.md skill
lijunzh/koda · koda-skills/skills/debug/SKILL.md · Diagnose koda issues — checks provider config, API connectivity, settings, and environment.
git:20261116.c35b66a · audit A · 15 stars
remember SKILL.md skill
lijunzh/koda · koda-skills/skills/remember/SKILL.md · Review the notes Koda saved and propose promotions, cleanups, and deduplication across all memory layers.
git:20261116.c35b66a · audit A · 15 stars
security-audit SKILL.md skill
lijunzh/koda · koda-skills/skills/security-audit/SKILL.md · Security vulnerability scan — finds vulnerabilities before attackers do
git:20261116.c35b66a · audit A · 15 stars
simplify SKILL.md skill
lijunzh/koda · koda-skills/skills/simplify/SKILL.md · Review changed code for reuse, quality, and efficiency — then fix any issues found.
git:20261116.c35b66a · audit A · 15 stars

Every file in lijunzh/koda

Other files named create-agent

create-agent SKILL.md skill
tailcallhq/forgecode · .forge/skills/create-agent/SKILL.md · Create new agents for the code-forge application. Agents are stored as .md files in the <cwd>/.forge/agents directory…
git:20260126.0427bf8 · audit A · 7,634 stars
create-agent SKILL.md skill
asymmetric-al/core · .agents/skills/create-agent/SKILL.md · Guides a one-question-at-a-time design interview, captures alignment in agent/EVE-BRIEF.md, then scaffolds and…
git:20260628.294b019 · audit A · 370 stars
create-agent SKILL.md skill
openma-ai/open-managed-agents · skills/create-agent/SKILL.md · Help users create and configure openma managed agents through conversation. Trigger when users say "create an agent"…
git:20260415.053b4a7 · audit A · 364 stars
create-agent SKILL.md skill
fairladyz625/harness-anything · skills/create-agent/SKILL.md · Create or update a Harness Anything business Agent — a declared identity with its own instructions, prompts, skills…
git:20261026.06196ea · audit A · 234 stars
create-agent SKILL.md skill
harness/harness-skills · skills/agents/create-agent/SKILL.md · Create and update Harness AI agent instances - standalone templates for agentic workflows in pipelines. Use when asked…
v1.0.0 · audit A · 134 stars
create-agent SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/create-agent/SKILL.md · Create a new agent definition file following the agent-almanac agent template and registry conventions. Covers persona…
v1.0 · audit A · 45 stars
create-agent SKILL.md skill
khaledsaeed18/dotclaude · skills/engineering/create-agent/SKILL.md · Author a new subagent for this repository end to end by scaffolding it with pnpm new, curating its tool allowlist…
git:20260921.234cab4 · audit A · 5 stars

Browse by kind, by grade A, or by owner.