create-agent

A skill that turns the current conversation into a reusable nui agent definition and saves it as an agent file. The definition includes the agent's instructions and basic configuration.

In plain words
What is it for?
Use it to create or update an agent based on the conversation, including its name, purpose, prompt, working setup, and optional recurring first message.
Why use it?
It saves you from rebuilding the same agent instructions by hand when a useful workflow should be reused.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/plmbr/nui/create-agent
Any agent
npx skills add plmbr/nui --skill create-agent
Clone the repo
git clone --depth 1 https://github.com/plmbr/nui

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00668
Opus 5 $0.00012 $0.00334
Sonnet 5 $0.00005 $0.00134
Haiku 4.5 $0.00002 $0.00067

Measured 2d ago against content hash 7133ce58a885, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

internal/skills/builtins/create-agent/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Agent

Use this skill when the user invokes /create-agent or asks you to turn the conversation into a reusable nui agent.

Default behavior

When no other instructions are given, convert the conversation into a new ADL agent definition:

  1. Infer a short id (kebab-case, e.g. code-review-helper) and human-readable name.
  2. Write a description summarizing what the agent does.
  3. Distill the conversation into a systemPrompt that captures the user's intent, constraints, and examples discussed.
  4. If the conversation implies a recurring first message, set defaultPrompt; otherwise omit it.
  5. Choose harness.type from context (default claude-code when unclear).
  6. Omit aiAssets, steps, and env unless the conversation clearly requires them.

Save the result as ~/.nui/agents/<id>.yaml.

When the user adds instructions

Follow any instructions in the same message after /create-agent or in follow-up messages. Examples:

  • change harness, model, or working directory behavior
  • add skills, MCP servers, or workflow steps
  • rename the agent or adjust the system prompt
  • update an existing agent file instead of creating a new one

User instructions override the default conversion behavior when they conflict.

ADL template

Use ADL 1.0. Minimum viable agent:

adl: "1.0"

id: example-agent
name: Example Agent
description: One-line summary of what this agent does.
version: 0.1.0

harness:
  type: claude-code
  model: claude-sonnet-4-6

systemPrompt: |
  Instructions distilled from the conversation.

Optional fields when relevant: defaultPrompt, promptMode, workingDirInput, env, aiAssets, steps.

Saving

  • Target directory: ~/.nui/agents/
  • Filename: <id>.yaml (must match the id field)
  • Create the directory if needed.
  • If a file with the same id already exists, ask before overwriting unless the user explicitly requested an update.

API harness (no Write tool)

When you do not have filesystem Write/Edit tools, call save_agent on the nui-agent MCP server with the full YAML in the content field. Set overwrite to true only when updating an existing agent the user asked to replace.

Read the full file on GitHub · 78 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 78 lines · 24 tokens per session scan A 7133ce58a885

Subscribe to this mod's changes

create-agent is a skill published in the GitHub repository plmbr/nui (5 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 668 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

doubt-driven-review

In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…

BlackBeltTechnology/pi-agent-dashboard · 90 tokens

release-cut

Cut a new pi-agent-dashboard release: promote ## [Unreleased] in CHANGELOG.md, bump every workspace package.json per SemVer, commit, tag v , and push — triggering the Release workflow that publishes every non-private workspace, builds the Electron artifacts, and creates a GitHub Release. Use on "cut a release"…

BlackBeltTechnology/pi-agent-dashboard · 93 tokens

ship-it

Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…

BlackBeltTechnology/pi-agent-dashboard · 92 tokens

faq-mine

Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…

BlackBeltTechnology/pi-agent-dashboard · 94 tokens

session-to-guideline

Turn a pi session into a Markdown "how-we-did-it" collaboration guideline: reads the session's JSONL transcript and synthesizes a reusable playbook of which prompts worked, what had to be steered, and how to reproduce the result faster. Use when: "document this session", "write up how we did X with the AI", "make a…

BlackBeltTechnology/pi-agent-dashboard · 93 tokens

scenario-design

Draft real-life test SCENARIOS (not smoke tests) from a change/feature spec. Derives edge-case, performance, frontend-quirk and error-handling scenarios with ISTQB techniques, routes each to a test level, and writes test-plan.md, emitting clarification questions on a spec gap. Use on "design test scenarios", "what…

BlackBeltTechnology/pi-agent-dashboard · 88 tokens