okr

okr is a skill for Claude Code, Codex from tupe12334/instinct. It costs 16 tokens per session (2,250 once invoked), scanned A, original, MIT.

A quarterly planning method built around Objectives, which describe a desired outcome, and Key Results, which measure whether it was reached.

In plain words
What is it for?
Use it to set company, team, or individual goals, connect work to those goals, and review progress during the quarter.
Why use it?
It turns broad team ambitions into a small set of measurable results that can be checked regularly.

Skill for Claude CodeCodex

Part of the instinct plugin — 54 skills, 1 hook shipped together

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 skills/tupe12334/instinct/okr
Any agent
npx skills add tupe12334/instinct --skill okr
Clone the repo
git clone --depth 1 https://github.com/tupe12334/instinct

Made for: Claude Code, Codex.

Or install instinct, the plugin that ships this one along with the rest of its 54 skills, 1 hook.

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 okr

README.md
[![agentmods](https://agentmods.dev/badge/skills/tupe12334/instinct/okr.svg)](https://agentmods.dev/skills/tupe12334/instinct/okr)
Your own site
<a href="https://agentmods.dev/skills/tupe12334/instinct/okr"><img src="https://agentmods.dev/badge/skills/tupe12334/instinct/okr.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,250 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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.02250
Opus 5 $0.00008 $0.01125
Sonnet 5 $0.00003 $0.00450
Haiku 4.5 $0.00002 $0.00225

Measured 4d ago against content hash 812c21221a04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

okr 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 4d 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.

skills/okr/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OKR — Objectives and Key Results

Overview

OKRs link ambition to evidence. An Objective answers "where do we go?" — it is qualitative, inspiring, and time-boxed. Key Results answer "how will we know we got there?" — they are numeric, binary, and unambiguous. Teams typically run OKRs on a quarterly cadence with a weekly check-in.

Company OKR
└── Team OKR (supports company O)
    ├── KR 1 — numeric target
    ├── KR 2 — numeric target
    └── KR 3 — numeric target
        └── Individual Initiative (drives KR 3)

One Objective, 2–5 Key Results. Any more and focus collapses.

Core Components

Objective

A short, memorable statement of the outcome you want. It should be:

  • Qualitative — no numbers; those belong in KRs
  • Ambitious — uncomfortable but not absurd (70% confidence of hitting it is a good target)
  • Time-boxed — scoped to the quarter
  • Motivating — a team should feel why this matters

Bad: "Improve the product" Good: "Make onboarding so fast that new users reach their first win within 10 minutes"

Key Results

2–5 measurable outcomes that collectively prove the Objective was achieved. Each KR must:

  • Have a baseline (where you are now) and a target (where you need to be)
  • Be outcome-based, not a task ("ship X" is an initiative, not a KR)
  • Be independently verifiable — two people with the data should agree whether it was hit

Bad KR: "Run five customer interviews" (output, not outcome) Good KR: "Increase activation rate from 28% to 45%"

Initiatives

The work you do to move KRs. Initiatives are not OKRs — they are the bets you make. Track them separately. If an initiative isn't moving a KR, stop it.

Layer Example Type
Objective Dominate the SMB market in DACH Qualitative
Key Result 1 Grow DACH SMB ARR from €400k to €700k Numeric outcome
Key Result 2 Achieve NPS ≥ 45 among DACH SMB accounts Numeric outcome
Key Result 3 Win rate vs. top competitor from 30% to 50% Numeric outcome
Initiative Launch German-language onboarding flow Task (feeds KR 2 & 3)

Read the full file on GitHub · 143 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. 4d ago First seen · 143 lines · 16 tokens per session scan A 812c21221a04

Subscribe to this mod's changes

okr is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 18d ago), licensed MIT. It adds 16 tokens to every session and 2,250 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 2026-08-31.