WORKFLOW

WORKFLOW is an agent for coding agents from aAAaqwq/AGI-Super-Team. It costs 0 tokens per session (302 once invoked), scanned A, original, MIT.

A portable workflow for generic AI-agent roles, covering how to understand a request, plan work, make local changes, and review the result.

In plain words
What is it for?
Use it to structure coding-agent tasks, identify actions needing approval, record assumptions, and check completed work.
Why use it?
It provides a shared process for handling constraints, approvals, available tools, evidence, testing, and rollback.

Agent

Part of the agi-super-team plugin — 53 skills, 3 agents shipped together

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/aaaaqwq/agi-super-team/workflow
Clone the repo
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team

Or install agi-super-team, the plugin that ships this one along with the rest of its 53 skills, 3 agents.

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.

agentmods badge for WORKFLOW

README.md
[![agentmods](https://agentmods.dev/badge/agents/aaaaqwq/agi-super-team/workflow.svg)](https://agentmods.dev/agents/aaaaqwq/agi-super-team/workflow)
Your own site
<a href="https://agentmods.dev/agents/aaaaqwq/agi-super-team/workflow"><img src="https://agentmods.dev/badge/agents/aaaaqwq/agi-super-team/workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00302
Opus 5 $0.00000 $0.00151
Sonnet 5 $0.00000 $0.00060
Haiku 4.5 $0.00000 $0.00030

Measured 3d ago against content hash b75aa4950447, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

WORKFLOW 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.

agents/WORKFLOW.md · 35 lines

What it actually says

🔁 Portable role workflow

This workflow is copied into every generic role workspace. A harness supplies models, tools, delegation, and scheduling; none of those capabilities are assumed to exist.

1. Brief

  • Restate the requested outcome, audience, constraints, and non-goals.
  • Identify external writes, credentials, money, publishing, deployment, or destructive actions that require human approval.
  • Inspect only the local files and capabilities actually available.

2. Plan

  • Choose the smallest relevant local skills.
  • Split independent work only when the harness exposes a delegation capability.
  • Name artifacts, owners, dependencies, acceptance checks, and rollback.
  • If scheduling is requested, provide a schedule proposal; do not claim it is active until the harness confirms it.

3. Build

  • Keep changes local and reversible.
  • Preserve existing user, persona, and skill files.
  • Record assumptions and source evidence beside the artifact.
  • Stop before any unapproved external or irreversible action.

4. Review

  • Run the relevant deterministic checks.
  • Ask the domain owner or Governor role for independent review when available.
  • Separate structural evidence from semantic quality and runtime outcomes.
  • Report missing capabilities or evidence as Validation pending.

5. Release handoff

Provide artifact paths, changes, verification, limitations, approvals still required, and rollback. Never report a delegated task, schedule, publication, deployment, or transaction as complete without observable confirmation from the active harness or human operator.

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 · 35 lines · 0 tokens per session scan A b75aa4950447

Subscribe to this mod's changes

WORKFLOW is an agent published in the GitHub repository aAAaqwq/AGI-Super-Team (90 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 302 tokens. 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.