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.
npx skills add tupe12334/instinct --skill the-grow-modelgit clone --depth 1 https://github.com/tupe12334/instinctWrote 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.
[](https://agentmods.dev/skills/tupe12334/instinct/the-grow-model)<a href="https://agentmods.dev/skills/tupe12334/instinct/the-grow-model"><img src="https://agentmods.dev/badge/skills/tupe12334/instinct/the-grow-model.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.02132 |
| Opus 5 | $0.00012 | $0.01066 |
| Sonnet 5 | $0.00005 | $0.00426 |
| Haiku 4.5 | $0.00002 | $0.00213 |
Grade A, and why
the-grow-model 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The GROW Model
Overview
A 4-stage framework for structured coaching conversations, problem-solving sessions, and goal achievement. Originally developed by Sir John Whitmore.
G — Goal What do you want to achieve?
R — Reality Where are you now?
O — Options What could you do?
W — Will What will you do?
GROW moves from aspiration → current state → possibilities → commitment. Each stage builds on the last.
Stages
G — Goal
Define a clear, motivating target. The goal should be specific enough to know when it's reached.
Key questions:
- What do you want to achieve?
- What would success look like?
- By when?
- Why is this important to you?
- How will you know you've reached it?
- What would achieving this give you?
Tips:
- Distinguish between end goals (ultimate outcome) and performance goals (what you directly control)
- Make it challenging but believable
- Apply smart/pure/clear criteria to sharpen the goal
R — Reality
Assess the current situation honestly, without judgment. This stage grounds the conversation in facts.
Key questions:
- What is happening now?
- What have you already tried?
- What's working? What's not?
- What resources do you have?
- What's blocking you?
- On a scale of 1–10, where are you relative to your goal?
- What do others say about this situation?
Tips:
- Stay descriptive, not evaluative — "what is" not "what should be"
- Surface assumptions that may be constraining thinking
- Don't rush to solutions here; understanding the reality fully is the work
O — Options
Generate the widest possible set of potential actions before narrowing. This stage is divergent thinking.
Key questions:
- What could you do?
- What else? (ask this 3–5 times)
- What would you do if [constraint] didn't exist?
- What would someone you admire do?
- What have others done in similar situations?
- What's the smallest possible step?
- What's the boldest possible move?
Tips:
- Don't evaluate options during generation — capture everything
- Aim for at least 5–7 options; more is better
- Include "do nothing" as an option to make its costs explicit
- After generation, evaluate each option on feasibility and impact
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.
- 7d ago First seen · 193 lines · 24 tokens per session scan A 3c62a04f14ae
the-grow-model is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 21d ago), licensed MIT. It adds 24 tokens to every session and 2,132 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.
Other skills, from other repositories
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
thinking-lindy-effect
Use when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the proven.
thinking-kepner-tregoe
Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.