What is workflow-team?

A guided process for delivering large or risky software changes with several specialised workers. It assigns coordination, implementation, review, and adversarial checking according to the size and risk of the work.

Use it for changes across more than ten files, several modules, or work that needs parallel workers and a deliberate review stage.

It separates planning, building, review, and final challenge so that one worker does not make every decision unchecked. It is intended for work spanning many files or modules, or involving security or data risk.

workflow-team — Skill for Claude Code by irahardianto/awesome-agv

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.

Any agent

npx skills add irahardianto/awesome-agv --skill workflow-team

Clone the repo

git clone --depth 1 https://github.com/irahardianto/awesome-agv

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/irahardianto/awesome-agv/workflow-team/github.svg)](https://agentmods.dev/skills/irahardianto/awesome-agv/workflow-team)

Your own site

<a href="https://agentmods.dev/skills/irahardianto/awesome-agv/workflow-team"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/workflow-team/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/irahardianto/awesome-agv/workflow-team"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/workflow-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,619 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.02619
Opus 5.5	$0.00014	$0.01048
Sonnet 5.5	$0.00007	$0.00524
Haiku 4.5	$0.00003	$0.00262

Measured 10d ago against content hash 84bc78287601, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

workflow-team scanned grade C with 1 finding 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| **10a. Deliver** | Overseer | Present report → promote docs → `rm -rf .agentwork/` |

.agents/skills/workflow-team/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/workflow-team

Entry-point guard: This is a user-invoked command skill (/workflow-team). If you are a spawned subagent, do NOT execute this skill — return to your assigned scope card.

You are @overseer. STOP — read your full protocol FIRST before reading anything else in this file: file://{workspace}/.agents/agents/overseer.md

Your ONLY job: spawn @conductor, relay user approvals, spawn @red-team-lead after build+review, and deliver the final report. You never implement, never decompose, never dispatch tech-leads/builders/reviewers/scouts/designers, never give implementation instructions, never make technical decisions.

§3–§4 below are reference material for the CONDUCTOR, not for you. The conductor reads its own role file for the full details. You do NOT use the Tech-Lead, Builder, Reviewer, or Scout templates — those are exclusively for the conductor and tech-leads to use when they dispatch their own children.

Use /workflow-team when work spans >10 files, touches 3+ modules, involves security/data risk, or needs adversarial review. For smaller tasks, use /workflow-solo.

§0. Spawn Protocol (Universal `TypeName="self"` Pattern)

Spawn Rule. In Antigravity, all subagents across all tiers are spawned using TypeName="self". This ensures the subagent inherits the full toolset (write tools, terminal execution, subagent spawning) needed to perform its work autonomously. Role differentiation and domain boundaries are enforced through the Role field, the system prompt, and the agent's role file in .agents/agents/{role}.md.

invoke_subagent(
  TypeName: "self",                              ← ALWAYS "self" to inherit full toolset
  Role:     "Conductor",                         ← Descriptive role for this instance
  Prompt:   "Read your role file FIRST:          ← Points to role file
             file://{workspace}/.agents/agents/conductor.md
             Your workspace is: {workspace}
             Your task: ..."
)

Read the full file on GitHub · 195 lines

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.

10d ago First seen · 195 lines · 34 tokens per session scan C 84bc78287601

Subscribe to this mod's changes

workflow-team is a skill published in the GitHub repository irahardianto/awesome-agv (156 stars, last pushed 10d ago), licensed MIT. It adds 34 tokens to every session and 2,619 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.

Building agents Planning ai-agent ai-coding best-practices coding-standards framework generative-ai

android-finance-spec

Use when generating, reviewing, or refactoring Android Kotlin code for financial apps that require BigDecimal/String precision, RTL/i18n safety, Kotlin style discipline, and "do not reinvent existing project patterns" constraints.

brycegao/android-finance-spec · 48 tokens

om-system-extension

Extend installed Open Mercato modules through UMES enrichers, interceptors, mutation guards, widgets, menus, entity extensions, events, component/page replacements, and overrides. Use for "extend core", "add field/column/action", "hide page", "intercept API", "UMES", or "rozszerz moduł".

open-mercato/open-mercato · 73 tokens

om-evolve-harness

Add a reproducible standalone agent-harness use case or correct failed routing/context with semantic assertions, one knowledge owner, and before/after evaluation. Use for "add harness case", "agent got this wrong", "extend the harness", "new use case", or "rozszerz harness".

open-mercato/open-mercato · 66 tokens

om-build-workflow

Build or extend standalone business workflows, activities, event triggers, durable user tasks, compensation, output paths, idempotency, and live progress. Use for "add workflow", "custom activity", "CALLAPI", "approval task", "workflow progress", or "zbuduj workflow".

open-mercato/open-mercato · 63 tokens

om-troubleshooter

Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.