Borrowing it
Nothing to install: this file belongs to frankxai/Starlight-Intelligence-System. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frankxai/Starlight-Intelligence-System/main/.claude/commands/training-coach-trainer.mdgit clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-SystemWrote 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/commands/frankxai/starlight-intelligence-system/training-coach-trainer)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/training-coach-trainer"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/training-coach-trainer/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/commands/frankxai/starlight-intelligence-system/training-coach-trainer"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/training-coach-trainer.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 | $0.00072 | $0.02550 |
| Opus 5 | $0.00036 | $0.01275 |
| Sonnet 5 | $0.00014 | $0.00510 |
| Haiku 4.5 | $0.00007 | $0.00255 |
Grade A, and why
training-coach-trainer 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/training-coach-trainer
Load agents/starlight-training.md, skills/people-intelligence/learning-architecture.md, and the Curriculum + Program Design for the program the SME will deliver. Produce a Train-the-Trainer Plan that converts a subject-matter-expert into a facilitator.
Why this exists
Most internal trainers are subject-matter-experts who have never been taught how adults learn. They lecture (because lecture is what they experienced as students). They overload (because they want to "cover everything"). They confuse "I covered it" with "they got it." They skip retrieval (because retrieval feels like quizzing, which feels infantilizing). They run out of time on simulation (because simulation is uncomfortable for them as much as for learners). They skip debrief (because debrief requires holding silence).
None of this is the SME's fault. They were never taught. TtT teaches them.
Without TtT, the cascade is broken. The curriculum survives; the delivery doesn't. Refuse SME deployment without TtT complete.
Input
$ARGUMENTS
Flags
--delivery-date <YYYY-MM-DD>— required. The TtT must complete at least 2 weeks before delivery for cohort facilitation practice to land.--sme-experience <none|some|experienced>— optional. None = full TtT (4-6 sessions). Some = focused TtT (2-3 sessions). Experienced = facilitation refresh + program-specific brief.
Process
-
Verify program design exists. No curriculum + program design → halt. Route to
/training-curriculumand/training-program-design. -
Assess SME baseline. What does this SME know about adult learning? About facilitation? About this specific program? The TtT plan adapts to the answer.
-
Build the TtT curriculum — meta-curriculum for the SME, 4-6 sessions for SMEs without facilitation background:
Session 1 — Adult learning principles (condensed Knowles). Adults need: relevance to their problem, autonomy in how they engage, prior experience honored, problem-centered (not subject-centered) framing, motivation tied to self-concept. The SME unlearns the lecture-as-transmission model.
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.
- 6d ago First seen · 179 lines · 72 tokens per session scan A a31de34eef9a
training-coach-trainer is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 2,550 once invoked, about $0.0004 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.
Other commands, from other repositories
memories
View and manage learned memories.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.
learn
Add new learning to memory.
gbu-retro
Post-session retrospective — harvest this session's lessons into durable doctrine.
agent-list
List all available agents with their capabilities (MPM-provided — may be shadowed by a user /agent-list command).