Borrowing it
Nothing to install: this file belongs to MarkDonish/round-table-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MarkDonish/round-table-workspace/main/.codex/skills/agent-builder-skill/SKILL.mdgit clone --depth 1 https://github.com/MarkDonish/round-table-workspaceWrote 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/markdonish/round-table-workspace/agent-builder-skill)<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/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/markdonish/round-table-workspace/agent-builder-skill"><img src="https://agentmods.dev/badge/skills/markdonish/round-table-workspace/agent-builder-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00029 | $0.00518 |
| Opus 5.5 | $0.00012 | $0.00207 |
| Sonnet 5.5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
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 2mo 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 — 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.mdconfig/agent-registry.jsonschemas/agent-manifest.schema.jsonschemas/agent-registry.schema.jsonschemas/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
- Do not claim live Nuwa execution unless a future runtime command actually runs and persists that evidence.
- Do not inject a full persona
SKILL.mdinto round-table context. - Round-table meetings should consume
roundtable-profile.mdandagent.manifest.jsonmetadata. - People-like labels are cognitive lenses, not voice-imitation instructions.
- New agents must not enter automatic selection until explicitly enabled.
- 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>
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.
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.
- 2mo ago First seen · 71 lines · 29 tokens per session scan A 045f675a87c3
agent-builder-skill is a skill published in the GitHub repository MarkDonish/round-table-workspace (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 518 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
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…