temporal-worker-knowledge

temporal-worker-knowledge is a skill for Claude Code, Cursor from redhat-community-ai-tools/UnifAI. It costs 36 tokens per session (1,431 once invoked), scanned A, original, Apache-2.0.

A reference guide for a Temporal worker that runs MAS agent sessions as durable, distributed workflows. Temporal is a workflow system that can resume long-running work after crashes or interruptions.

In plain words
What is it for?
Use it when editing the Temporal worker, session workflows, graph traversal, workflow activities, worker registration, or distributed node execution.
Why use it?
It clarifies which code controls workflow lifecycle, graph traversal, individual agent nodes, and replay-safe execution.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: paths in frontmatter, but also installed under .cursor/.

Good fit Use it when editing the Temporal worker, session workflows, graph traversal, workflow activities, worker registration, or distributed node execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhat-community-ai-tools/unifai/temporal-worker
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 redhat-community-ai-tools/UnifAI --skill temporal-worker
Clone the repo
git clone --depth 1 https://github.com/redhat-community-ai-tools/UnifAI

Made for: Claude Code, Cursor.

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 temporal-worker-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/temporal-worker/github.svg)](https://agentmods.dev/skills/redhat-community-ai-tools/unifai/temporal-worker)
Your own site
<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/temporal-worker"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/temporal-worker/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.

agentmods 80×15 button for temporal-worker-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/temporal-worker"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/temporal-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,431 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00036 $0.01431
Opus 5 $0.00018 $0.00715
Sonnet 5 $0.00007 $0.00286
Haiku 4.5 $0.00004 $0.00143

Measured 10d ago against content hash 6ebb52c2419d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

temporal-worker-knowledge 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 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.

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.

.cursor/skills/codebase/domains/temporal-worker/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Temporal Worker Knowledge System

Distributed workflow execution service for MAS agent sessions. Shares the multi-agent/ codebase — Temporal workflows and activities are adapters wrapping MAS domain services.

For domain logic, load the MAS domain skill (../multi-agent/SKILL.md).

Role

  • Executes agent session workflows via Temporal (durable, crash-recoverable)
  • Runs distributed graph execution across workers
  • Handles workflow lifecycle (start, signal, cancel, timeout)
  • Provides Temporal replay guarantees for long-running agent sessions

Key Files

File Role
adapters/inbound/temporal/worker.py Worker registration: workflows + activities
adapters/inbound/temporal/workflows/session_workflow.py SessionWorkflow — top-level lifecycle
adapters/inbound/temporal/workflows/graph_traversal_workflow.py GraphTraversalWorkflow — BSP supersteps
adapters/inbound/temporal/activities/graph_node_activities.py GraphNodeActivities — execute one node
adapters/inbound/temporal/activities/session_lifecycle_activities.py Begin/complete/fail transitions
lib/mas/engine/distributed/node_executor.py NodeExecutor — materializes mini-blueprint, runs node
lib/mas/engine/distributed/traversal.py GraphTraversal — BSP superstep algorithm
lib/mas/session/execution/lifecycle_handler.py BackgroundLifecycleHandler — thin adapter for activities

Workflow Structure

Temporal Server → dispatch → SessionWorkflow (parent)
    → begin_session activity
    → GraphTraversalWorkflow (child) — BSP supersteps:
        → plan: which nodes are ready?
        → execute_graph_node activities (parallel per node)
        → evaluate_condition activities
        → merge results → repeat
    → complete_session / fail_session activity

Activities (Temporal adapters)

Activity Class Purpose
execute_graph_node GraphNodeActivities Run one node via NodeExecutor
evaluate_condition GraphNodeActivities Check edge conditions
begin_session SessionLifecycleActivities Session status → RUNNING
complete_session SessionLifecycleActivities Session status → COMPLETED
fail_session SessionLifecycleActivities Session status → FAILED

Read the full file on GitHub · 162 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. 10d ago First seen · 162 lines · 36 tokens per session scan A 6ebb52c2419d

Subscribe to this mod's changes

temporal-worker-knowledge is a skill published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,431 once invoked, about $0.0002 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.