agent-builder-skill

agent-builder-skill is a skill for Claude Code, Codex from MarkDonish/round-table-workspace. It costs 29 tokens per session (518 once invoked), scanned A, original, MIT.

A local tool for turning generated or imported skills into agent descriptions, profiles, and registry entries. It prepares agents for possible selection in a shared workspace but does not run meetings or debates.

In plain words
What is it for?
Use it to create or import agent definitions, validate their manifests and registries, and manage which candidate agents are available.
Why use it?
It provides a defined process for checking, registering, enabling, and disabling candidate agents before they are used.

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/markdonish/round-table-workspace/agent-builder-skill
Any agent
npx skills add MarkDonish/round-table-workspace --skill agent-builder-skill
Clone the repo
git clone --depth 1 https://github.com/MarkDonish/round-table-workspace

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agent-builder-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/markdonish/round-table-workspace/agent-builder-skill.svg)](https://agentmods.dev/skills/markdonish/round-table-workspace/agent-builder-skill)
Your own site
<a href="https://agentmods.dev/skills/markdonish/round-table-workspace/agent-builder-skill"><img src="https://agentmods.dev/badge/skills/markdonish/round-table-workspace/agent-builder-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 518 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 $0.00029 $0.00518
Opus 5 $0.00015 $0.00259
Sonnet 5 $0.00006 $0.00104
Haiku 4.5 $0.00003 $0.00052

Measured 4d ago against content hash 045f675a87c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-builder-skill 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 4d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (runtime/agent_manifest.py, runtime/agent_registry.py, runtime/validate_agent_bundle.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.codex/skills/agent-builder-skill/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Builder Skill

Agent Builder connects Nuwa-style generated skills to the Round Table Workspace agent ecosystem.

It does not run /room or /debate by itself. It prepares candidate agents so the selection layer can later decide whether they should enter a meeting.

Explicit Commands

  • /agent-create <person or topic>
  • /agent-import <skill-path>
  • /agent-validate <agent-id or manifest-path>
  • /agent-register <manifest-path>
  • /agent-enable <agent-id>
  • /agent-disable <agent-id>

In the current backend slice, live Nuwa creation is not claimed. Use manifest, profile, and registry validation paths first.

Source Of Truth

  • docs/agent-factory-architecture.md
  • config/agent-registry.json
  • schemas/agent-manifest.schema.json
  • schemas/agent-registry.schema.json
  • schemas/agent-selection-request.schema.json
  • .codex/skills/agent-builder-skill/WORKFLOW.md
  • .codex/skills/agent-builder-skill/runtime/
  • examples/agent-factory/

The existing built-in runtime pool remains agents/registry.json. Agent Factory's config/agent-registry.json is the custom/candidate library for new or imported participants.

Hard Boundaries

  1. Do not claim live Nuwa execution unless a future runtime command actually runs and persists that evidence.
  2. Do not inject a full persona SKILL.md into round-table context.
  3. Round-table meetings should consume roundtable-profile.md and agent.manifest.json metadata.
  4. People-like labels are cognitive lenses, not voice-imitation instructions.
  5. New agents must not enter automatic selection until explicitly enabled.
  6. Fixture and metadata validation are not host-live or provider-live support.

Runtime Entry

Use:

python3 .codex/skills/agent-builder-skill/runtime/validate_agent_bundle.py ...
python3 .codex/skills/agent-builder-skill/runtime/agent_registry.py ...

The unified CLI also exposes:

./rtw agent list
./rtw agent validate
./rtw agent register <manifest>
./rtw agent enable <agent-id>
./rtw agent disable <agent-id>

Read the full file on GitHub · 71 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 71 lines · 29 tokens per session scan A 045f675a87c3

Subscribe to this mod's changes

agent-builder-skill is a skill published in the GitHub repository MarkDonish/round-table-workspace (2 stars, last pushed 20d ago), licensed MIT. It adds 29 tokens to every session and 518 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.