First 90 Days Playbook

First 90 Days Playbook is a skill for Claude Code from BrennanJCollins/UnabatedPM-coaching. It costs 70 tokens per session (3,548 once invoked), scanned A, original, MIT.

A coaching playbook for starting a new product-management role during the first 90 days. It focuses on learning the customer journey, understanding workplace incentives, and building influence through competence and credibility.

In plain words
What is it for?
Use it to create or review a 30/60/90-day onboarding plan. It guides what to learn first, how to demonstrate value, and when to take the lead.
Why use it?
It helps new, promoted, or transferred product managers avoid making decisions before they understand customers, colleagues, and the organization.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the unabatedpm-influence plugin — 8 skills, 1 command shipped together

Good fit Use it to create or review a 30/60/90-day onboarding plan. It guides what to learn first, how to demonstrate value, and when to take the lead.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brennanjcollins/unabatedpm-coaching/first-90-days-playbook
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.

Any agent
npx skills add BrennanJCollins/UnabatedPM-coaching --skill first-90-days-playbook
Clone the repo
git clone --depth 1 https://github.com/BrennanJCollins/UnabatedPM-coaching

Made for: Claude Code.

Or install unabatedpm-influence, the plugin that ships this one along with the rest of its 8 skills, 1 command.

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 First 90 Days Playbook

README.md
[![agentmods](https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/first-90-days-playbook/github.svg)](https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/first-90-days-playbook)
Your own site
<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/first-90-days-playbook"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/first-90-days-playbook/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 First 90 Days Playbook

Your own site · 80×15
<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/first-90-days-playbook"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/first-90-days-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,548 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 $0.00070 $0.03548
Opus 5 $0.00035 $0.01774
Sonnet 5 $0.00014 $0.00710
Haiku 4.5 $0.00007 $0.00355

Measured 12d ago against content hash 59226d1eae6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

First 90 Days Playbook 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 12d 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-influence/skills/first-90-days-playbook/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operating Modes

This skill operates in two modes:

Conversation mode (default): Coach the PM through building a 90-day onboarding plan using the absorb-then-direct sequence. Triggered by direct invocation or natural conversation.

Evaluate mode: Read an onboarding plan, 30/60/90 plan, or transition document silently, score its adherence to the framework, and return structured findings. No conversation, no questions — just assessment. Triggered by the /audit orchestrator.

Evaluate Mode Instructions

When invoked in evaluate mode, you receive a 90-day plan, onboarding document, or transition strategy. Do NOT coach. Do NOT ask questions. Read and score.

Score each dimension 1-5:

  • 1 = Not present or fundamentally broken (jumping to directing, skipping absorption)
  • 2 = Attempted but significant gaps (skipping phases, no customer immersion)
  • 3 = Competent but sequencing issues (absorb present but weak, directing too early)
  • 4 = Strong with clear phase structure and customer focus
  • 5 = Exemplary — Absorb → Demonstrate → Lead sequence, customer-first, hidden incentives understood

Dimensions to evaluate:

  1. Stakeholder alignment — Does the plan follow the Competence → Credibility → Influence sequence? Does Phase 1 prioritize ABSORBING before directing? Are there concrete customer immersion steps (customer interviews, journey mapping)? Does it show understanding of hidden incentives (what gets your boss/boss's boss fired)? Does it remove "requirements" language in favor of hypotheses?

  2. Market & customer intelligence — Does the plan show a week-by-week customer immersion strategy in Days 1-30? Does it map the customer journey before proposing solutions? Does it articulate the organizational power structure and decision-making dynamics? Does it avoid jumping to strategy changes in week 1?

Red flags to check:

  • Trying to change strategy in Days 1-14 (skipping absorption)
  • No customer interview or journey mapping plan
  • No organizational power structure or hidden incentives analysis
  • Jumping to "first win" before demonstrating competence
  • Language showing "requirements" instead of hypotheses
  • No evidence of listening to team feedback first
  • Immediate process improvements proposed without context
  • Proposing roadmap changes before understanding customer
  • No mention of understanding org dynamics or hidden priorities above

Read the full file on GitHub · 292 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. 12d ago First seen · 292 lines · 70 tokens per session scan A 59226d1eae6b

Subscribe to this mod's changes

First 90 Days Playbook is a skill published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (4 stars, last pushed 22d ago), licensed MIT. It adds 70 tokens to every session and 3,548 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.