smart

A goal checklist based on five criteria: specific, measurable, achievable, relevant, and time-bound.

In plain words
What is it for?
It is for writing and checking actionable goals for projects, tasks, and plans.
Why use it?
It turns vague intentions into goals with a clear result, way to measure progress, realistic scope, purpose, and deadline.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,642 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 $0.00019 $0.01642
Opus 5 $0.00010 $0.00821
Sonnet 5 $0.00004 $0.00328
Haiku 4.5 $0.00002 $0.00164

Measured yesterday against content hash eebea63ec56f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smart 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 yesterday.

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/SMART/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

smart Goals

Overview

smart is a criteria checklist for well-formed goals. A goal passing all 5 criteria is actionable, trackable, and achievable.

Letter Criterion Question to test
S Specific What exactly will be accomplished? Who is involved? Where?
M Measurable How will you know when it's achieved? What metrics?
A Achievable Is it realistic given your resources and constraints?
R Relevant Does it align with broader objectives? Does it matter now?
T Time-bound By what date? What are the interim milestones?

Criterion Breakdowns

S — Specific

Vague goals produce vague results. A specific goal answers:

  • What needs to be accomplished?
  • Who is responsible?
  • Where does it happen?
  • What constraints or conditions apply?

Bad: "Improve sales" Good: "Increase monthly recurring revenue from existing customers in the Enterprise segment"

M — Measurable

You can't manage what you can't measure. Measurable goals have:

  • A numeric target or binary completion state
  • A defined baseline (where you start from)
  • Leading indicators you can track weekly, not just a lagging outcome

Bad: "Get more users" Good: "Reach 500 active users (up from 200 current) measured by weekly logins"

A — Achievable

Challenging but within reach. Test:

  • Do you have or can you acquire the resources required?
  • Have others achieved something comparable?
  • What's the historical rate of progress on this metric?

Bad: "10× revenue in 30 days" (if not backed by a concrete plan) Good: "25% revenue growth this quarter, based on pipeline size and historical close rate"

R — Relevant

Aligned with what actually matters. Ask:

  • Does this goal serve your top-level mission or strategy?
  • Is this the right time for this goal?
  • Does it conflict with other priorities?

Bad: "Optimize the onboarding flow" when the company has a retention crisis Good: "Increase 30-day retention rate, the primary driver of LTV"

Read the full file on GitHub · 155 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. yesterday First seen · 155 lines · 19 tokens per session scan A eebea63ec56f

Subscribe to this mod's changes

smart is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 16d ago), licensed MIT. It adds 19 tokens to every session and 1,642 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.