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-startgit 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-start)<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-agent-team-start"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-agent-team-start/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/muratsilahtaroglu/claude-code-starter-kit/keel-agent-team-start"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-agent-team-start.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 | $0.00062 | $0.01732 |
| Opus 5 | $0.00031 | $0.00866 |
| Sonnet 5 | $0.00012 | $0.00346 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
keel-agent-team-start 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.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/keel-agent-team-start @ — who am I in this chat
When: the FIRST message of a newly-opened session that should act as one of the project's team
agents (/keel-agent-team-start @mechanic), or to SWITCH an existing chat's identity. The roster is
.claude/agents/team-*.md (created owner-approved by /keel-agent-team-create) — if no charters
exist, say so and stop; NEVER invent one (charter creation is the owner's, §10.42).
1. Resolve the agent
- Argument given (
@<name>or<name>): match againstteam-<name>.md. No match → list the roster once, ask. - No argument: if the reground hook already injected "this session is @X" into this context, confirm and jump to step 3 (idempotent — a known identity is never re-asked); otherwise ask ONCE with the roster.
2. Record the mapping — this is what survives compaction
- Session id: take it from the reground hook's
Session-id: <id>line in this context (the hook prints it whenever team charters exist). If it is genuinely absent, adopt the identity for this context anyway and WARN: "mapping not recorded — identity may need re-adopting after the next compact". - Append to
.claude/agent-team-sessions(git-ignored, machine-local):<session_id> <name> <YYYY-MM-DD>. If THIS session id already has a line, REPLACE that line (identity switch). Keep the file ≤ ~50 lines — drop the oldest. - Double-claim guard: if ANOTHER session id maps to the same agent with a recent date (≤ ~2 days), warn — "@ also looks active in another chat: takeover, or a collision about to happen?" — and proceed only on the owner's word (two chats writing one lane = the §10.42 clobber).
2b. Name the session after the agent — this is the messaging ADDRESS
Ask the owner to run /rename <name> in this chat (or relaunch it with claude --name <name>).
This is not cosmetic. The orchestrator wakes a worker with SendMessage, and its to: is the
SESSION name that /list-agents shows — not the keel agent name. A session nobody renamed is named
after the working directory, so a five-agent team reads as my-app-3f, my-app-a1, my-app-7c…
mutually indistinguishable: the orchestrator cannot address a worker, and the star-topology wall
cannot recognise a target as a teammate (it allows what it cannot identify, by design).
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.
- 4d ago Changed · +27 lines c1b88361dfa2
- 8d ago First seen · 68 lines · 62 tokens per session scan A 5d2eb4ef6610
keel-agent-team-start is a skill published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,732 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.