What is task-workflow?

A task-queue workflow for creating, claiming, updating, and completing work items shared by multiple AI agents. A dependency is a task that must be finished before another task can start.

Use it to split large jobs into smaller tasks, delegate work to other agents, run independent tasks in parallel, and enforce task dependencies.

It prevents agents from taking the same work and makes task status and ordering visible. It also supports blocked and cancelled work.

task-workflow — Skill for Claude Code and Codex by fthsrbst/mnema

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 fthsrbst/mnema --skill task-workflow

Clone the repo

git clone --depth 1 https://github.com/fthsrbst/mnema

Made for: Claude Code, Codex.

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/fthsrbst/mnema/task-workflow/github.svg)](https://agentmods.dev/skills/fthsrbst/mnema/task-workflow)

Your own site

<a href="https://agentmods.dev/skills/fthsrbst/mnema/task-workflow"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/task-workflow/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/fthsrbst/mnema/task-workflow"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/task-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 803 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00045	$0.00803
Opus 5.5	$0.00018	$0.00321
Sonnet 5.5	$0.00009	$0.00161
Haiku 4.5	$0.00005	$0.00080

Measured 1mo ago against content hash a823bb65d45a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-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 1mo 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.

skills/task-workflow/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Görev İş Akışı (Task Workflow)

Hub görev kuyruğu, agent'lar arası iş delegasyonunu sağlar. Bir agent iş oluşturur, başka bir agent (veya aynı agent farklı oturumda) o işi üstlenir ve tamamlar.

Görev Yaşam Döngüsü

pending → claimed → in_progress → done
                  ↘ blocked ↗
                  ↘ cancelled

Ne Zaman Görev Oluşturmalı

Durum	Aksiyon
Büyük iş parçalara bölünebilir	Her parça için ayrı görev
Başka agent'ın uzmanlığı gerekli	`agent_find` ile uygun agent bul, görev oluştur
Paralel çalışılabilir alt işler var	Bağımsız görevler oluştur
Sıralı bağımlılık var	`depends_on` ile zincirle

MCP Araçları

task_create

{
  "title": "API endpoint'lerini test et",
  "description": "Tüm REST endpoint'lerinin smoke test'i",
  "project": "my-project",
  "priority": 5,
  "tags": ["testing", "api"],
  "created_by": "claude-code"
}

task_claim

Bir görevi üstlenmek için:

{ "uid": "task-uid", "agent": "cursor-agent" }

Sadece pending durumundaki görevler claim edilebilir
Bağımlılıkları (depends_on) tamamlanmamış görevler claim edilemez

task_update

Durum değiştirmek için:

{ "uid": "task-uid", "status": "in_progress" }

task_complete

İşi bitirince:

{ "uid": "task-uid", "result": "15 endpoint test edildi, 2 hata bulundu" }

result alanına yapılandırılmış çıktı koy — sonraki agent bu bilgiyi kullanır

task_queue

Proje için sıradaki işleri almak için:

{ "project": "my-project", "limit": 5 }

Önceliğe göre sıralı, bağımlılıkları karşılanmış görevleri döner

Bağımlılık Yönetimi

{
  "title": "Frontend'i backend'e bağla",
  "depends_on": ["backend-api-uid", "auth-uid"]
}

depends_on içindeki tüm görevler done olmadan bu görev claim edilemez
Döngüsel bağımlılık oluşturma

Öncelik (Priority)

0 = normal (varsayılan)
1-5 = artan aciliyet
10+ = kritik (sadece gerçekten acil durumlar için)

En İyi Pratikler

Read the full file on GitHub · 93 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.

1mo ago First seen · 93 lines · 45 tokens per session scan A a823bb65d45a

Subscribe to this mod's changes

task-workflow is a skill published in the GitHub repository fthsrbst/mnema (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 803 once invoked, about $0.0002 per session on Opus 5.5. 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.

Project management ai-agents claude cli codex local-first mcp

task-workflow