agentflow

A system that uses a Kanban board—a board of work cards and stages—to coordinate several AI coding workers through research, building, testing, review, and integration.

In plain words
What is it for?
Dispatching multiple Claude Code workers, running code checks before review, tracking task costs, monitoring progress, and managing an AI development pipeline.
Why use it?
It keeps task state in tools such as Asana, GitHub Projects, or Linear, so progress remains visible and can recover after a session stops. It also lets people intervene by moving cards.

Skill for Claude CodeCodex

Part of the agent-harness plugin — 35 skills, 9 commands, 12 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 skills/ghosteken/agent-harness/agentflow
Any agent
npx skills add Ghosteken/agent-harness --skill agentflow
Clone the repo
git clone --depth 1 https://github.com/Ghosteken/agent-harness

Made for: Claude Code, Codex.

Or install agent-harness, the plugin that ships this one along with the rest of its 35 skills, 9 commands, 12 agents.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00052 $0.01953
Opus 5 $0.00026 $0.00977
Sonnet 5 $0.00010 $0.00391
Haiku 4.5 $0.00005 $0.00195

Measured 2d ago against content hash c28cac9851b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentflow 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 2d 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.

Origin

This is a copy

100% identical to agentflow — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

archive/skills-community/agentflow/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentFlow

Overview

AgentFlow turns your existing Kanban board into a fully autonomous AI development pipeline. Instead of building custom orchestration infrastructure, it treats your project management tool (Asana, GitHub Projects, Linear) as a distributed state machine — tasks move through stages, AI agents read and write state via comments, and humans intervene through the same UI they already use.

The result is complete pipeline observability from your phone, free crash recovery (state lives in your PM tool, not in memory), and human override at any point by dragging a card.

When to Use This Skill

  • Use when you need to orchestrate multiple Claude Code workers across a full development lifecycle (build, review, test, integrate)
  • Use when you want deterministic quality gates (tsc/eslint/tests) before AI review on AI-generated code
  • Use when you want full pipeline visibility from your Kanban board or phone
  • Use when running a solo or team project that needs autonomous task dispatch with cost tracking
  • Use when you need crash-proof orchestration that survives session restarts

Core Concepts

7-Stage Kanban Pipeline

Tasks flow through: Backlog, Research, Build, Review, Test, Integrate, Done. Each stage has specific gates. The Kanban board IS the orchestration layer — no separate database, no message queue, no custom infrastructure.

Stateless Orchestrator

A crontab-driven one-shot sweep runs every 15 minutes. No daemon, no session dependency. If it crashes, the next sweep picks up where it left off because all state lives in your PM tool.

Deterministic Before Probabilistic

Hard gates (tsc + eslint + tests) run before any AI review, catching roughly 60% of issues at near-zero cost. AI review comes after, as a second layer.

Adversarial Review

A different AI agent reviews code and must list 3 things wrong before deciding to pass. This prevents rubber-stamp approvals.

Transitive Priority Dispatch

Tasks that unblock the most downstream work get built first, automatically computing the critical path.

Read the full file on GitHub · 205 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.

  1. 2d ago First seen · 205 lines · 52 tokens per session scan A c28cac9851b6

Subscribe to this mod's changes

agentflow is a skill published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 17d ago), licensed MIT. It adds 52 tokens to every session and 1,953 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agentflow, differing in 0 lines, and is treated as a copy.