team-supervisor

A background agent that watches a multi-step work pipeline as it runs. It checks quality and reports on the pipeline's health at key points.

In plain words
What is it for?
Use it to monitor agent workflows, observe results between checkpoints, and flag quality or health issues during execution.
Why use it?
It helps catch problems between steps instead of waiting until the whole pipeline finishes. It also gives the team a regular view of whether the work is progressing correctly.

Agent for Claude Code

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 agents/catlog22/maestro-flow/team-supervisor
Clone the repo
git clone --depth 1 https://github.com/catlog22/maestro-flow

Made for: Claude Code.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,745 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00022 $0.01745
Opus 5 $0.00011 $0.00873
Sonnet 5 $0.00004 $0.00349
Haiku 4.5 $0.00002 $0.00175

Measured 3d ago against content hash df76a8952fa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-supervisor 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 3d 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.

.claude/agents/team-supervisor.md · 146 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 3d ago First seen · 146 lines · 22 tokens per session scan A df76a8952fa6

Subscribe to this mod's changes

team-supervisor is an agent published in the GitHub repository catlog22/maestro-flow (537 stars, last pushed 9d ago), with no licence file. It adds 22 tokens to every session and 1,745 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 2026-08-30.

Related

Other agents, from other repositories

creating-extensions

Как устроены skill (skills//SKILL.md), определение агента (packs//agents/.yaml) и pack. Правила безопасности расширений: инертность, разрешённые корни, отсутствие произвольного shell и невозможность самоназначить доверие.

romarayt/raytsystem-public-os · 58 tokens

README

This folder consolidates, in a single location, the SoT for the project's five multi-agent roles plus the Universal Cycle skeleton. It is modeled on the role system of a Korean newspaper, and each role is self-contained in its capability boundary, I/O contract, and prompt template.

alfadur7/llm-wiki-newsroom · 0 tokens

editor-in-chief

Entry point for the 9 slash commands + agent routing + publish gate + ADAPT escalation counter + log operation + invoking the deterministic tools (build/lint/export/fetch). The meta layer outside the matrix — governs flow above every cycle. Does not author content directly (routing only).

alfadur7/llm-wiki-newsroom · 61 tokens

prompt_engineer

Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…

josstei/maestro-orchestrate · 98 tokens

index

Host-computed coding-agent activity and resume-identity observability — a live, read-only view of what each terminal's agent is doing, plus an honest resume hint when a session's backend dies uncleanly. The companion to ctx.processes (foreground process facts); this surface is for agent activity and resume identity.…

silo-code/silo · 0 tokens

kun-codex-lane-protocol

Status: installed and authenticated locally on 2026-07-03. Lane name: Kun. Tooling: standalone Codex CLI at /Users/duhokim/.local/bin/codex. Default model: gpt-5.5, same model family as Tori/Hermes Codex route. Wrapper: /Users/duhokim/.local/bin/kun-codex.

DuhoKim/NebulaMind · 0 tokens