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 muratsilahtaroglu/claude-code-starter-kit --skill keel-agent-team-creategit clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kitWrote 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/muratsilahtaroglu/claude-code-starter-kit/keel-agent-team-create)<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-agent-team-create"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-agent-team-create.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.02155 |
| Opus 5 | $0.00034 | $0.01077 |
| Sonnet 5 | $0.00014 | $0.00431 |
| Haiku 4.5 | $0.00007 | $0.00215 |
Grade A, and why
keel-agent-team-create 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 7d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/keel-agent-team-create — build the agent team (owner-only)
When: the owner wants parallel Claude sessions in THIS repo to work like a specialized team
(orchestrator · mechanic · frontend · test · provider…) instead of ad-hoc co-agents. This wizard
CREATES the structure once; each chat later adopts an identity via /keel-agent-team-start @<name>.
(Real human teams on different machines are /keel-team's job, not this one — the two can coexist:
human lanes and agent lanes share the same TASKS board, and creation authority is the owner's in both.)
0. Owner gate (hard — creation is governance)
.claude/project-ownerexists andgit config user.name≠ its content → STOP: "agent-team creation is owner-only — ask @". (The owner-guard hook independently blocks non-owner writes to.claude/agents/*; this check just fails politely and earlier.).claude/project-ownermissing → offer to write it FIRST (arming owner-guard): a team without a declared owner has no enforceable governance. Only proceed after it exists.
1. Interview the owner (ask, don't assume)
- How many agents, and their names — single English tokens preferred (
orchestrator,mechanic,frontend,test,provider…); the owner's naming always wins. Exactly ONE agent carries the orchestrator role. - A task-id prefix per lane — derived from the names, confirmed by the owner:
co-agent→co,frontend→fro,provider→prv; the orchestrator gets none (it takes no work items). That lane's items then runco1 · co2 · co3 …, allocated by the orchestrator alone so two sessions can't mint the same number. 2–4 lowercase letters, unique across BOTH the agent and the human roster, never reused, never renamed — the id also namesreports/team/<name>/co3_*,<id>_spec.mdandscratch/co3/, so renaming dangles permanent artifacts (§9.32, §10.40). One case only: a series split acrossr1andR28makes every count wrong (field case). - Each worker's domain — mission (one line), scope paths (globs), anything it must NEVER touch.
- Charter/prompt language — EN or TR (the project's docs language usually decides). Note the invariant either way: machine-memory writes (boards, HANDOVER/LESSONS input) are ENGLISH (§9.31).
- Review routing notes — the default is review-v2 (rules §10.41): the orchestrator routes every
review and delegates the mechanical half to the
verifiersubagent; name any area that instead deserves a DEDICATED reviewer agent (rare — each extra agent is a chat window the owner must steer).
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.
- 7d ago First seen · 110 lines · 69 tokens per session scan A 36d8a2023592
keel-agent-team-create is a skill published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 2,155 once invoked, about $0.0003 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.
Other skills, from other repositories
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
security-audit
Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.