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 double-diamondgit 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/double-diamond)<a href="https://agentmods.dev/skills/tupe12334/instinct/double-diamond"><img src="https://agentmods.dev/badge/skills/tupe12334/instinct/double-diamond/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.
<a href="https://agentmods.dev/skills/tupe12334/instinct/double-diamond"><img src="https://agentmods.dev/badge/skills/tupe12334/instinct/double-diamond.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.02283 |
| Opus 5.5 | $0.00010 | $0.00913 |
| Sonnet 5.5 | $0.00005 | $0.00457 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
double-diamond 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Double Diamond
Overview
The Double Diamond is a design process model developed by the UK Design Council in 2005. It structures creative problem-solving into two back-to-back cycles of divergent and convergent thinking: the first diamond ensures you are solving the right problem; the second ensures you solve it right. Skip the first diamond and you risk building the wrong thing elegantly.
┌──────────────────────────────┬──────────────────────────────┐
│ DIAMOND 1 │ DIAMOND 2 │
│ "Are we solving the │ "Are we solving the │
│ right problem?" │ problem right?" │
├──────────────┬───────────────┼──────────────┬───────────────┤
│ DISCOVER │ DEFINE │ DEVELOP │ DELIVER │
│ (diverge) │ (converge) │ (diverge) │ (converge) │
├──────────────┼───────────────┼──────────────┼───────────────┤
│ Research │ Synthesize │ Ideate │ Prototype │
│ Observe │ Reframe │ Build drafts │ Test & learn │
│ Empathize │ Define HMW │ Experiment │ Ship or kill │
└──────────────┴───────────────┴──────────────┴───────────────┘
Phase Definitions
Discover — Diverge to understand the problem space
Open up. The goal is to gather raw evidence before forming opinions.
- Conduct user interviews, field observations, diary studies, or competitive reviews.
- Do not filter yet. Capture contradictions, edge cases, and surprises.
- Outputs: interview transcripts, observation notes, data, market research.
Define — Converge to frame the right problem
Close down. Synthesize everything from Discover into a single, testable problem statement.
- Cluster insights by theme (affinity mapping).
- Write a "How Might We" (HMW) question that is neither too broad ("improve healthcare") nor too narrow ("add a button on screen 3").
- Validate the framing: could solving this HMW address the root causes surfaced in Discover?
- Outputs: insight themes, HMW problem statement, design brief.
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.
- 1mo ago First seen · 135 lines · 25 tokens per session scan A f1bfa3da1441
double-diamond is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 2,283 once invoked, about $0.0001 per session on Opus 5.5. 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-triz
When two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, then invent a concrete no-compromise resolution.
s4h-design-constraints
Uses constraints productively — maps hard limits, soft preferences, and how the tightest constraints define the solution space. Triggers: 'what are the design constraints', 'map the constraints', 'what are we working within', 'what's fixed', 'constraint-driven design', 'what does the solution space look like'…
s4h-design-iteration
Structures the feedback loop between making and learning — prototyping, testing, and convergence toward fit. Triggers: 'prototype and test', 'iterate on the design', 'how do we test this', 'get feedback on the design', 'what should we prototype', 'design feedback loop', 'test and learn', 'are we converging'.
s4h-design-simplicity
Applies the design principle of removing rather than adding — finding the form that does exactly what is needed, nothing more. Triggers: 'simplify this', 'remove what's unnecessary', 'it's too complicated', 'what can we cut', 'reduce the design', 'it's bloated', 'make it simpler', 'find the essential form', 'what's…
s4h-aesthetic-coherence-check
Tests whether the parts of something form a unified whole — finding the jarring inconsistencies that accumulate when different contributors work without a shared vision. TRIGGERS: 'coherence check', 'does this feel unified', 'something feels off', 'inconsistent', 'check the whole', 'does this hang together'.
s4h-aesthetic-pattern-detection
Identifies the underlying formal pattern at work — because most successful designs, arguments, and solutions share deep structural patterns, and naming the pattern unlocks the playbook. TRIGGERS: 'what pattern is this', 'pattern recognition', 'why does this work', 'identify the form', 'what structure is at play'…