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 jxoesneon/Ciel --skill team-buildergit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/team-builder)<a href="https://agentmods.dev/skills/jxoesneon/ciel/team-builder"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/team-builder/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/jxoesneon/ciel/team-builder"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/team-builder.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 | $0.00033 | $0.00898 |
| Opus 5 | $0.00016 | $0.00449 |
| Sonnet 5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
team-builder 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 9d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Team Builder (Interactive Agent Composition)
This skill provides an interactive agent-picker UX for composing teams by capability profile. While ciel-swarm-orchestration automatically decomposes tasks and assigns sub-agents, team-builder is human-in-the-loop: the user browses available agent personas, selects which to deploy, and defines the task interactively. Use this when the user wants deliberate control over team composition rather than automatic dispatch.
When to Use
- You have multiple agent personas and want to pick which ones to use for a task.
- You want to compose an ad-hoc team from different domains (e.g., Security + SEO + Architecture).
- You want to browse what agents are available before deciding.
Agent Discovery
Agents are discovered via two methods, merged and deduplicated by name:
claude agentscommand (primary): Returns all agents known to the CLI — user agents, plugin agents (prefixedplugin-name:), and built-in agents.- File glob (fallback): Reads markdown from
./agents/**/*.md,~/.claude/agents/**/*.md.
Precedence on name collision: user agents > plugin agents > built-in agents. Built-in agents (Explore, Plan) are skipped unless explicitly requested.
Domain Grouping
- Subdirectory layout: Domain inferred from parent folder name (e.g.,
engineering/security-engineer.md→ Engineering). - Flat layout: Domain inferred from shared filename prefixes. A prefix qualifies as a domain only if 2+ files share it. Unique-prefix files go to "General". Splits at first
-, so multi-word domains should use subdirectory layout.
Selection Flow
- Discover: Run
claude agents, parse output, read markdown files for names/descriptions. - Present Domain Menu: Show domains with agent counts; skip empty domains.
- Handle Selection: Accept flexible input — numbers ("1,3"), names ("security + seo"), or "all from engineering". If >5 agents selected, ask user to narrow down (max 5 per team).
- Confirm: Show selected agents, prompt for task description.
- Spawn in Parallel: Read each agent's markdown, spawn all via parallel Agent tool calls with
subagent_type: "general-purpose". Each runs independently. - Synthesize: Collect outputs, present unified report grouped by agent with a synthesis section (agreements, conflicts/tensions, next steps). Skip synthesis if only 1 agent selected.
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.
- 9d ago First seen · 65 lines · 33 tokens per session scan A c68e159713aa
team-builder is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 33 tokens to every session and 898 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
ai-native-software-dev
Use when the user asks to build, change, modernize, or reconstruct non-trivial software with an AI-native workflow, including greenfield development, work in an existing codebase, or authorized reference-based product reconstruction; also use when lifecycle planning, architecture, implementation, testing, review…
ticket-spec
Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.
Code Quality Review
Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.
redpolicy-guide
An editorial policy for turning webinar transcripts into self-contained guides. A transcript is a written record of spoken material, while a self-contained guide can be understood without watching the webinar.
write-overview
A workflow for researching and writing a review essay about a project topic when no finished source text exists. It gathers the facts, studies example essays when available and produces the article in a project output folder.