Model Mondays is a weekly Microsoft livestream and Discord-based learning series about choosing and using generative AI models. Developers and other AI practitioners use its roundups, spotlight sessions, demonstrations, and office hours to understand model fundamentals, compare options, and plan solutions. The catalogue contains an instruction related to the series.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/model-mondaysnpx agentmods add skills/microsoft/model-mondays/refresh-episodeWrote 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/skills/microsoft/model-mondays/refresh-episode)<a href="https://agentmods.dev/skills/microsoft/model-mondays/refresh-episode"><img src="https://agentmods.dev/badge/skills/microsoft/model-mondays/refresh-episode/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/skills/microsoft/model-mondays/refresh-episode"><img src="https://agentmods.dev/badge/skills/microsoft/model-mondays/refresh-episode.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 | $0.00069 | $0.01939 |
| Opus 5.5 | $0.00028 | $0.00776 |
| Sonnet 5.5 | $0.00014 | $0.00388 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
refresh-episode 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 14d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Episode
Update an existing Model Mondays episode with newly available, approved material. Refresh only the requested episode and information; do not create an episode or batch-update other episodes unless explicitly asked.
Invocation
Accept a season/episode identifier and the requested update, with an optional source path. Examples:
refresh-episode S4:E03 with the latest slidesrefresh-episode s4-e03 with data/assets/slides/S04-E03-Model-Router.pdfrefresh-episode S4:E06 with the supplied recording and resourcesrefresh-episode S4:E03 with link to replay <url>
Repository Contract
Read root AGENTS.md and applicable local instructions before editing. This
skill is reusable across seasons; resolve current metadata instead of hardcoding
Season 4 dates, titles, speakers, or counts.
- Metadata:
data/livestreams.json. - Pages:
docs/model-mondays/YYYY-MM-DD-sNN-eNN.md. - Public assets:
docs/assets/model-mondays/. - Season indexes: root
README.mdanddocs/index.md. - Uploaded source decks may be under
data/assets/slides/; these are inputs, not public download destinations. Do not add new assets todata/assets/. - Final Season 4 banners are authoritative for date, title, host, and guests.
- Use supplied, approved material only, relative repository links, and "Microsoft Foundry" in prose. Never fabricate details or publish placeholders.
- Preserve unrelated worktree changes and historical content.
Workflow
1. Resolve the Episode and Source
- Normalize
S4:E03,S04:E03, ors4-e03to season 4, episode 3, and the existing stable IDs4-e03. Look up the unique matching JSON record. - Use its date and zero-padded season/episode numbers to locate the page. For
example, S4:E03 currently resolves to
docs/model-mondays/2026-08-24-s04-e03.md. Read it before changing anything. - Use an explicitly supplied source path first. Otherwise, inspect supplied
assets for the matching season/episode, including
data/assets/slides/and the public asset tree. Match numeric IDs, not just a topic name. - For example,
data/assets/slides/S04-E03-Model-Router.pdfbelongs to S4:E03. Do not assume other episodes already have slides or use their decks. - If the episode or source is missing, stop and request the missing input. If multiple revisions match and the intended deck is unclear, ask which to use; file modification time alone does not establish the approved latest version.
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.
- 14d ago First seen · 161 lines · 69 tokens per session scan A 17a35b38a5ca
refresh-episode is a skill published in the GitHub repository microsoft/model-mondays (301 stars, last pushed 9d ago), licensed MIT. It adds 69 tokens to every session and 1,939 once invoked, about $0.0003 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 2026-10-03.
Other skills, from other repositories
economy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
vibe-agents
Create project agent instructions and tool configuration from agreed product and technical decisions.
vibe-prd
Write or revise an MVP product requirements document with scope and observable acceptance criteria.
vibe-research
Research an app idea or resolve product and technical uncertainties before committing to a design.
vibe-techdesign
Write an MVP technical design from agreed requirements, including architecture choices and relevant tradeoffs.
vibe-workflow
Select the appropriate planning, implementation, or debugging workflow for an app project.