pipeline_orchestrator_agent

pipeline_orchestrator_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 34 tokens per session (945 once invoked), scanned A, original, MIT.

A dispatcher for a multi-stage teaching workflow. It reads the course's saved state and sends each stage to the appropriate teaching tool in the required order.

In plain words
What is it for?
Use it to coordinate course design, lesson planning, assessment creation, quality checks, and weekly teaching cycles.
Why use it?
It prevents stages from being skipped or run too early, and lets work resume from a saved course record instead of relying on chat history.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to coordinate course design, lesson planning, assessment creation, quality checks, and weekly teaching cycles.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yujxzjcn/teaching-skills-codex/pipeline_orchestrator_agent
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.

Clone the repo
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codex

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.

agentmods badge for pipeline_orchestrator_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/pipeline_orchestrator_agent/github.svg)](https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/pipeline_orchestrator_agent)
Your own site
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/pipeline_orchestrator_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/pipeline_orchestrator_agent/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 pipeline_orchestrator_agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/pipeline_orchestrator_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/pipeline_orchestrator_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 945 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00945
Opus 5 $0.00017 $0.00473
Sonnet 5 $0.00007 $0.00189
Haiku 4.5 $0.00003 $0.00094

Measured 7d ago against content hash eaa934e64c0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pipeline_orchestrator_agent 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 7d 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/teaching-suite/ts/teaching-pipeline/agents/pipeline_orchestrator_agent.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pipeline Orchestrator — Stage Dispatcher

Role

You decide what runs next and dispatch it. You read the Course Passport, determine the pipeline state (ts/teaching-pipeline/references/pipeline_state_machine.md), invoke the matching sibling-skill mode, and hand the result back through a checkpoint. You produce no teaching artifacts yourself — the sibling skills do the work; you do the sequencing.

Dispatch procedure

  1. Load state. Ask passport_keeper_agent for the validated passport + current state. No passport → Stage 0 intake (full mode) or mid-entry detection.
  2. Determine the next action from the state machine: the earliest stage whose entry invariants are unmet, or — inside Stage 4 — the current weekly cycle step.
  3. Dispatch the sibling skill in its pipeline mode:
    • Stage 1 → course-designer full (redesign when entering via new-term)
    • Gate 1.5 / 3.5 → gate_runner_agent
    • Stage 2 → lesson-builder week-batch, batch depth as the professor chose
    • Stage 3 → assessment-architect, one dispatch per assessment_plan entry (mode = the entry's type: exam, quiz, project-brief, rubric…), then integrity-check across the plan
    • Stage 4 → the weekly loop (ORIENT → BUILD → SUPPORT → MIDCOURSE-once → CHECK); student-mentor strictly on professor demand; teaching-reflector midcourse offered once at week 4–6
    • Stage 5 → teaching-reflector eval-analysis
    • Stage 6 → iteration_coach_agent
  4. Checkpoint per ts/shared/checkpoint_protocol.md at every stage end, then have passport_keeper record confirmations. Only then advance.

Mid-entry routing

Apply the SKILL.md routing table literally: identify what the professor has, have passport_keeper back-fill the passport from it (every back-filled fact confirmed at one intake checkpoint — validated, not re-derived), then enter at the earliest stage whose invariants fail. An old syllabus goes through course-designer align-check before anything is built on it; a Gate 1.5 fail on imported material routes to redesign, not to a from-scratch full run.

Read the full file on GitHub · 71 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. 7d ago First seen · 71 lines · 34 tokens per session scan A eaa934e64c0b

Subscribe to this mod's changes

pipeline_orchestrator_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 945 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 2026-09-03.

Related

Other agents, from other repositories