new-manager-first-90-days

new-manager-first-90-days is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 125 tokens per session (1,177 once invoked), scanned A, original, MIT.

A phased 90-day plan for someone starting as a manager. It begins with listening and learning, then moves to setting direction and improving how the team works.

In plain words
What is it for?
Use it to plan early one-on-ones, understand an inherited team, choose early wins, delegate work, build trust, and set priorities.
Why use it?
It helps new managers avoid changing everything too quickly or continuing to do all the work themselves. It treats team output, trust, delegation, and difficult conversations as the new responsibilities.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it to plan early one-on-ones, understand an inherited team, choose early wins, delegate work, build trust, and set priorities.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/new-manager-first-90-days
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,357 stars · on GitHub · mohitagw15856.github.io

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/mohitagw15856/pm-claude-skills

Made for: Cursor.

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 new-manager-first-90-days

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/new-manager-first-90-days/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/new-manager-first-90-days)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/new-manager-first-90-days"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/new-manager-first-90-days/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 new-manager-first-90-days

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/new-manager-first-90-days"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/new-manager-first-90-days.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,177 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 $0.00125 $0.01177
Opus 5 $0.00063 $0.00589
Sonnet 5 $0.00025 $0.00235
Haiku 4.5 $0.00013 $0.00118

Measured 8d ago against content hash 575656045abd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

new-manager-first-90-days 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 8d 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.

exports/cursor/pm-career/new-manager-first-90-days/new-manager-first-90-days.mdc · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Manager: First 90 Days

The jump to managing is a role change, not a promotion for doing more of the same — and most first-time managers stumble by either changing everything on day one or staying an individual contributor with a title. This gives a phased first-90-days plan: earn trust and learn first, then set direction, then adjust — plus how to handle the 1:1s, delegation, and hard conversations that define the job.

What This Skill Produces

  • A phased 90-day plan — listen & learn (first weeks) → set direction (mid) → adjust & build (later), instead of changing everything at once
  • First 1:1s — how to run them to build trust and understand each person (their goals, working style, and what they need from you)
  • The mindset shift — moving from doer to enabler: your output is now the team's output
  • Trap avoidance — the classic first-time mistakes (doing the work yourself, changing too fast, avoiding difficult conversations, playing favorites)
  • Early wins — credibility-building moves that help the team without overstepping
  • A read on the situation — inheriting a team vs. building one, peers-now-reports, or a struggling team

Required Inputs

Ask for these if not provided:

  • The situation — inherited team, new team, promoted over former peers, or a turnaround
  • The team — size, and what you know about how it's doing
  • Your background — first-time manager or experienced, and your relationship to the team
  • The context — org expectations, any pressing issues
  • Your worry — what you're most unsure about

Framework: Learn, Then Lead

  1. Listen before you change. Spend the early weeks understanding the team, the work, and the context before making changes — early sweeping changes without understanding destroy trust.
  2. Invest in 1:1s. Use first 1:1s to learn each person's goals, strengths, working style, and needs — relationships are the foundation of everything else.
  3. Make the mindset shift. Your job is now to enable the team, not to be the top individual contributor — resist doing the work yourself; delegate and develop.
  4. Set direction once you understand. After learning, clarify priorities, expectations, and how the team will work — then adjust based on what you see.
  5. Don't dodge the hard stuff. Address underperformance and tensions kindly but directly; avoiding difficult conversations early is a trap that compounds.
  6. Bank early, appropriate wins. Small improvements and removing blockers build credibility without overstepping your still-forming understanding.

Read the full file on GitHub · 72 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. 8d ago First seen · 72 lines · 125 tokens per session scan A 575656045abd

Subscribe to this mod's changes

new-manager-first-90-days is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 1,177 once invoked, about $0.0006 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.