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.
git clone --depth 1 https://github.com/YujxZJCN/teaching-skillsWrote 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.
[](https://agentmods.dev/agents/yujxzjcn/teaching-skills/pipeline_orchestrator_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/pipeline_orchestrator_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/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.
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/pipeline_orchestrator_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/pipeline_orchestrator_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.00937 |
| Opus 5.5 | $0.00014 | $0.00375 |
| Sonnet 5.5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00094 |
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 21d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- pipeline_orchestrator_agent — 97% identical, 4 lines differ
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 (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
- Load state. Ask
passport_keeper_agentfor the validated passport + current state. No passport → Stage 0 intake (fullmode) or mid-entry detection. - 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.
- Dispatch the sibling skill in its pipeline mode:
- Stage 1 →
course-designerfull(redesignwhen entering vianew-term) - Gate 1.5 / 3.5 →
gate_runner_agent - Stage 2 →
lesson-builderweek-batch, batch depth as the professor chose - Stage 3 →
assessment-architect, one dispatch perassessment_planentry (mode = the entry's type:exam,quiz,project-brief,rubric…), thenintegrity-checkacross the plan - Stage 4 → the weekly loop (ORIENT → BUILD → SUPPORT → MIDCOURSE-once → CHECK);
student-mentorstrictly on professor demand;teaching-reflectormidcourseoffered once at week 4–6 - Stage 5 →
teaching-reflectoreval-analysis - Stage 6 →
iteration_coach_agent
- Stage 1 →
- Checkpoint per
shared/checkpoint_protocol.mdat 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.
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.
- 21d ago First seen · 71 lines · 34 tokens per session scan A 4ac26c5c2621
pipeline_orchestrator_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills (41 stars, last pushed 22d ago), licensed MIT. It adds 34 tokens to every session and 937 once invoked, about $0.0001 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 2026-10-04.
Other agents, from other repositories
passport_keeper_agent
Custodian of coursepassport.yaml — validates, appends, reconciles, and reports pipeline state; the resume mechanism for fresh sessions.
gate_runner_agent
Executes the Alignment Gate (1.5) and Quality Gate (3.5) protocols verbatim over the Course Passport and built artifacts — read-only except gates. fields.
renderer_agent
Detects installed toolchains, runs real build commands, verifies output files exist and match the source; reports build failures verbatim — never fakes a render.
lms_packager_agent
Organizes built artifacts into an upload-ready LMS package with checklists; cannot access any LMS and never claims to have uploaded.
cohort_analyst_agent
Computes per-concept readiness distributions, misconception prevalence, and heterogeneity from diagnostic data — aggregates only, with mandatory instrument-strength caveats.
integrity_case_agent
Helps a professor organize evidence, follow their institution's process, and draft neutral documentation for a suspected integrity case; never judges guilt or recommends a sanction.