pure

pure is a skill for Claude Code, Codex from tupe12334/instinct. It costs 17 tokens per session (1,507 once invoked), scanned A, original, MIT.

A goal-checking framework that asks whether a goal is positively stated, understood, relevant, and ethical.

In plain words
What is it for?
It is for reviewing and improving the wording and quality of goals before pursuing them.
Why use it?
It helps reveal goals that are unclear, poorly framed, misaligned, or potentially harmful.

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/pure
Any agent
npx skills add tupe12334/instinct --skill pure
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 pure

README.md
[![agentmods](https://agentmods.dev/badge/skills/tupe12334/instinct/pure.svg)](https://agentmods.dev/skills/tupe12334/instinct/pure)
Your own site
<a href="https://agentmods.dev/skills/tupe12334/instinct/pure"><img src="https://agentmods.dev/badge/skills/tupe12334/instinct/pure.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,507 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 $0.00017 $0.01507
Opus 5 $0.00009 $0.00754
Sonnet 5 $0.00003 $0.00301
Haiku 4.5 $0.00002 $0.00151

Measured 3d ago against content hash 894cf54369f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pure 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 3d 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/PURE/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pure Goals

Overview

pure is a complementary goal-quality filter, often used alongside smart. It originates from NLP (neuro-linguistic programming) coaching and emphasizes the psychological and ethical framing of goals, not just their structure.

Letter Criterion Core question
P Positively stated Is the goal framed as what you want (not what you want to avoid)?
U Understood Is the goal clear to everyone involved?
R Relevant Is it aligned with broader priorities and the right time?
E Ethical Does achieving this goal align with your values and not harm others?

Criterion Breakdowns

P — Positively Stated

The brain moves toward what you focus on. Negatively framed goals ("stop missing deadlines", "don't lose customers") keep attention on the unwanted state.

Reframe toward the desired outcome:

Negative framing Positive reframe
"Stop being late to standups" "Arrive to every standup on time"
"Don't lose the enterprise deal" "Close the enterprise deal by [date]"
"Reduce bugs in production" "Ship zero-defect releases"

Test: Can you visualize and feel success? Negatively framed goals are hard to visualize.

U — Understood

The goal must be clear to every person who will act on it or be affected by it. No ambiguity in scope, ownership, or definition of done.

Test questions:

  • If you asked every team member to describe this goal, would they give the same answer?
  • Are all key terms defined? ("improve performance" — define "improve" and "performance")
  • Is ownership explicit?

If interpretation varies: rewrite until consensus is possible.

R — Relevant

Right goal at the right time. Connects to the bigger picture.

Ask:

  • Does this goal serve the current strategic priority?
  • Is the timing right? (If a dependency isn't ready, the goal may be premature)
  • Does pursuing this crowd out a higher-priority goal?

Read the full file on GitHub · 151 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. 3d ago First seen · 151 lines · 17 tokens per session scan A 894cf54369f7

Subscribe to this mod's changes

pure is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 17d ago), licensed MIT. It adds 17 tokens to every session and 1,507 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.