Upgrade

Upgrade is a command for Claude Code from BrennanJCollins/UnabatedPM-coaching. It costs 52 tokens per session (4,500 once invoked), scanned A, original, MIT.

A command that rewrites a product manager's document to a more senior standard and adds coaching notes explaining substantive changes. It returns the revised document in its original Word or PowerPoint format.

In plain words
What is it for?
Use it to upgrade product-management documents, including Word files and PowerPoint presentations, with annotations in Word comments or PowerPoint speaker notes.
Why use it?
It improves the document while showing what was changed and why. This helps the writer learn the communication principles behind the edits instead of receiving only a finished rewrite.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the unabatedpm-coaching-os plugin — 3 commands shipped together

Good fit Use it to upgrade product-management documents, including Word files and PowerPoint presentations, with annotations in Word comments or PowerPoint speaker notes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/brennanjcollins/unabatedpm-coaching/upgrade
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/BrennanJCollins/UnabatedPM-coaching

Made for: Claude Code.

Or install unabatedpm-coaching-os, the plugin that ships this one along with the rest of its 3 commands.

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 Upgrade

README.md
[![agentmods](https://agentmods.dev/badge/commands/brennanjcollins/unabatedpm-coaching/upgrade/github.svg)](https://agentmods.dev/commands/brennanjcollins/unabatedpm-coaching/upgrade)
Your own site
<a href="https://agentmods.dev/commands/brennanjcollins/unabatedpm-coaching/upgrade"><img src="https://agentmods.dev/badge/commands/brennanjcollins/unabatedpm-coaching/upgrade/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 Upgrade

Your own site · 80×15
<a href="https://agentmods.dev/commands/brennanjcollins/unabatedpm-coaching/upgrade"><img src="https://agentmods.dev/badge/commands/brennanjcollins/unabatedpm-coaching/upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,500 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 $0.00052 $0.04500
Opus 5 $0.00026 $0.02250
Sonnet 5 $0.00010 $0.00900
Haiku 4.5 $0.00005 $0.00450

Measured 10d ago against content hash 9194a40d6261, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Upgrade 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 10d 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.

unabatedpm-coaching-os/commands/upgrade.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the Upgrade command from the PM Coaching OS by Brennan Collins. Your job is to take a PM document, rewrite it to senior PM standard, annotate every substantive change with the framework that drove it, iterate until the score is maximized, and deliver the result in the document's native format. The user gets a better document they can open in Word or PowerPoint — AND learns how to write better documents from the coaching annotations.

Pre-Flight: Tier Check

Before starting, check if pm_assessment_data/assessments.jsonl exists in the user's folder. If it does:

  1. Count entries where "type": "upgrade" in the ledger
  2. Check for pm_assessment_data/credits.json. If it exists, read it:
    {
      "tier": "free|starter|pro|enterprise",
      "creditsRemaining": 0,
      "creditsUsedThisMonth": 1,
      "monthlyAllowance": 0,
      "resetDate": "ISO 8601 — first of next month",
      "grantType": null,
      "grantExpiry": null
    }
    
  3. Decision tree:
    • If tier is "starter", "pro", or "enterprise" AND creditsRemaining > 0: proceed normally. Decrement creditsRemaining and increment creditsUsedThisMonth after successful upgrade.
    • If tier is "starter", "pro", or "enterprise" AND creditsRemaining == 0: show credit exhaustion message: "You've used all [monthlyAllowance] upgrade credits this month. Credits reset on [resetDate]. Need more? Upgrade your plan at unabatedproducts.com/pm-assessment."
    • If no credits.json exists AND upgrade count in ledger >= 1: Soft gate. Show the user what they'd gain, but don't produce the upgraded file:
      • "You've used your free document upgrade. Your assessment shows [document] has upgrade potential — I can tell you what would change, but the full upgraded file requires premium access."
      • Present the evaluation and plan (Steps 1-4) so they see the value
      • End with: "Unlock unlimited upgrades at unabatedproducts.com/pm-assessment"
      • STOP here. Do not proceed to Step 5.
    • If no credits.json exists AND upgrade count < 1: proceed normally (first free upgrade).
  4. After a successful upgrade, if credits.json exists, write the updated credit counts back to the file.

Read the full file on GitHub · 358 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. 10d ago First seen · 358 lines · 52 tokens per session scan A 9194a40d6261

Subscribe to this mod's changes

Upgrade is a command published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (4 stars, last pushed 20d ago), licensed MIT. It adds 52 tokens to every session and 4,500 once invoked, about $0.0003 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 2026-08-31.