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.
npx skills add plmbr/nui --skill create-agentgit clone --depth 1 https://github.com/plmbr/nuiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/plmbr/nui/create-agent)<a href="https://agentmods.dev/skills/plmbr/nui/create-agent"><img src="https://agentmods.dev/badge/skills/plmbr/nui/create-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/plmbr/nui/create-agent"><img src="https://agentmods.dev/badge/skills/plmbr/nui/create-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 71 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00790 |
| Opus 5.5 | $0.00010 | $0.00316 |
| Sonnet 5.5 | $0.00005 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 89 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:
- Infer a short id (kebab-case, e.g.
code-review-helper) and human-readable name. - Write a description summarizing what the agent does.
- Distill the conversation into a systemPrompt that captures the user's intent, constraints, and examples discussed.
- If the conversation implies a recurring first message, set defaultPrompt; otherwise omit it.
- Choose harness.type from context (default
claude-codewhen unclear). - Omit aiAssets, orchestration, 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 orchestration (workflow steps, subAgents, or council)
- 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, orchestration.
For multi-agent agents use orchestration (never top-level steps, subAgents, or council):
orchestration:
type: workflow # or subAgents | council
steps: # when type is workflow
- name: review
systemPrompt: ...
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.
- 1mo ago Changed · +1 lines 6e5b21c018fd
- 1mo ago Changed · +10 lines f49bef3d3e4f
- 1mo ago First seen · 78 lines · 24 tokens per session scan A 7133ce58a885
create-agent is a skill published in the GitHub repository plmbr/nui (8 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 790 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
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…
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…
ci-troubleshoot
Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and retrigger jobs. Use when a CI run is red, a release is stuck, a workflow won't dispatch, or you need to know which workflow does…
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"…
anti-slop-frontend
A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…
spec-coherence-check
Sweep all active OpenSpec proposals for staleness, conflicts, and obsolescence against the current codebase and archived changes. Use when proposals may be outdated, when checking cross-proposal conflicts, or before starting a batch of implementations. Produces a gap-analysis report, updates a priority queue file, and…