A command that checks course files for Copilot information that may have become outdated, such as model names, prices, usage limits, release dates, and removed features.

Use it to audit Copilot course documentation, repository instructions, certification material, and files that mention specific models or features.

Software products change, so teaching material can quietly become incorrect after it was written. It compares those claims with current official information and reports possible changes.

freshen — Command by timothywarner

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.

agentmods

npx agentmods add commands/timothywarner/copilot-dev/freshen

Clone the repo

git clone --depth 1 https://github.com/timothywarner/copilot-dev

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 564 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00019	$0.00564
Opus 5	$0.00010	$0.00282
Sonnet 5	$0.00004	$0.00113
Haiku 4.5	$0.00002	$0.00056

Measured 2d ago against content hash 378fcdb176bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

freshen 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 2d 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.

.claude/commands/freshen.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are auditing this teaching repo for date-sensitive Copilot content that may have drifted since the last delivery. Today's date and the live README.md / COURSE_PLAN_MAY_*.md define "current" — verify everything else against those plus official sources.

Your task

Scan these files for date-sensitive facts (model names, prices, premium-request quotas, GA dates, feature names, deprecation lists):
- README.md
- The most recent COURSE_PLAN_*.md at the repo root
- CLAUDE.md
- docs/COPILOT_AGENT_TUTORIAL.md
- docs/COPILOT_CUSTOMIZATION_SAMPLES.md
- docs/latest-github-news.md
- docs/certification/*.md
- Any file under .github/agents/ or .github/instructions/ that names a specific model
Cross-check against authoritative sources using WebSearch and WebFetch:
- https://docs.github.com/en/copilot/reference/ai-models/supported-models
- https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals
- https://github.blog/changelog/ (filter for entries since the last delivery)
- https://github.com/github/copilot-cli/releases (latest CLI version)
Report findings as a single markdown table:

File Line Stale claim Current reality Suggested edit

Then a short "Headline since last delivery" summary (3-5 bullets) of what changed and what Tim should lead with on stage.

Rules

Do not edit anything. Report only. The user will decide which edits to apply.
If you cannot verify a fact (web search inconclusive), mark it UNVERIFIED rather than guessing.
Skip archive/ — it is preserved historical material, not current.
Skip the deliberately-deprecated demo file .github/chatmodes/new-mode.chatmode.md (kept for the rename teaching moment).
Skip the intentional bug in src/tip-lookup.js (line 35 — documented in its header).
The references/ and docs/references/ files (Microsoft Style Guide, fictional companies) are not date-sensitive — skip them.

Read the full file on GitHub · 44 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.

2d ago First seen · 44 lines · 19 tokens per session scan A 378fcdb176bc

Subscribe to this mod's changes

freshen is a command published in the GitHub repository timothywarner/copilot-dev (46 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 564 once invoked, about $0.0001 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.

Data and AI Git and workflow Learning and teaching

freshen

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Your task

Rules

What this file has done since we first saw it

Other commands, from other repositories

learn

component

memory-store

review

no-vibe

teach-me-testing