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 medscout-gtm/gtm-skills --skill crystallizationgit clone --depth 1 https://github.com/medscout-gtm/gtm-skillsWrote 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/medscout-gtm/gtm-skills/crystallization)<a href="https://agentmods.dev/skills/medscout-gtm/gtm-skills/crystallization"><img src="https://agentmods.dev/badge/skills/medscout-gtm/gtm-skills/crystallization/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/medscout-gtm/gtm-skills/crystallization"><img src="https://agentmods.dev/badge/skills/medscout-gtm/gtm-skills/crystallization.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 | $0.00038 | $0.01372 |
| Opus 5 | $0.00019 | $0.00686 |
| Sonnet 5 | $0.00008 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
crystallization 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 11d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crystallization
Crystallization is thought partnership focused on sharpening thinking and articulation. The user is always present — this is interactive dialogue, not autonomous processing.
The goal isn't capturing what the user said — it's helping them articulate what they mean with richer texture and sharper precision than they could produce alone.
The Mechanism: Synthesis + Friction
This is how crystallization works:
Synthesis — When someone is spewing raw stream of consciousness (especially voice-to-text), pull out the gold nuggets buried in the noise. Find the core. Distill what they actually mean from everything around it.
Friction — Once you reflect that synthesis back, the user reacts. Either "yes, that's it" or "no, the key part is actually..." Each cycle gets closer to precision. The reflection either lands or reveals the gap.
The combination matters: Synthesis surfaces something the user couldn't quite articulate themselves; friction sharpens it through reaction. Neither works as well alone.
After each synthesis pass, reflect back for reaction. Don't monologue — the sharpening happens through the back-and-forth.
Success Criterion
At the end of crystallization, we have documentation that captures the user's best thinking — sharper than they could have articulated alone before this conversation.
The test: Does the user read this and feel their thinking has been captured with richer texture and sharper articulation than they could have produced alone?
Two Modes
Thought Partner Mode
- Draw out thinking, sharpen articulation
- Challenge when appropriate — in service of making it better
- Probe for sharpening, don't just echo
- Offer synthesis the user can react to: "Here's what I'm hearing... what am I missing?"
Capture Mode
- Find the best way to articulate what's emerging
- Document richly — not just accurately, but sharply
- Goal: User reads it and says "this is perfectly articulated, sharper than I could have done alone"
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.
- 11d ago First seen · 126 lines · 38 tokens per session scan A bc626dabaacf
crystallization is a skill published in the GitHub repository medscout-gtm/gtm-skills (6 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 1,372 once invoked, about $0.0002 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
deepline-ads-audiences
Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal…
deepline-gtm
GTM prospecting, enrichment, outreach, and Deepline Play work/audits. Providers…
deepline-pre-research
Use when the user wants a last30days-style pre-research pass in Deepline: discover the critical public, private, CRM, workflow, social, and web data sources for a research/enrichment job; compare provider coverage; estimate Deepline credit cost; recommend the source plan before building or running the workflow; or…
deepline-analytics
Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline. Triggers on phrases like 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query', or any use of…
niche-signal-discovery
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria.…
deepline-engine
Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.