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 yogsoth-ai/north-star-crystallization --skill warm-startgit clone --depth 1 https://github.com/yogsoth-ai/north-star-crystallizationWrote 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/yogsoth-ai/north-star-crystallization/warm-start)<a href="https://agentmods.dev/skills/yogsoth-ai/north-star-crystallization/warm-start"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/north-star-crystallization/warm-start.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 | $0.00073 | $0.00694 |
| Opus 5 | $0.00036 | $0.00347 |
| Sonnet 5 | $0.00015 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
warm-start 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 8d 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.
This is a copy
86% identical to cold-start — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warm Start Strategy
The user has a general direction — they know the field or area but not the specific problem.
Questioning Protocol
All SOPs in this strategy follow these rules:
- One question at a time — never overwhelm with multiple questions
- Prefer multiple choice when possible — easier to answer
- Always allow "unsure" / "TBD" as legitimate answers
- Always ask WHY — not just "what do you want" but "why do you want it"
- After user answers: confirm understanding before continuing
- If user's answer reveals new information: immediately follow up
- If user declines to answer (privacy): accept, note that downstream work becomes broader/more iterative
Available Tactics
| Tactic | Purpose |
|---|---|
| actor-profiling | Understand who the user is |
| landscape-reconnaissance | Broad, shallow field exploration |
| direction-narrowing | Focus within chosen field(s) |
| obstacle-analysis | Identify and mitigate barriers |
| goal-decomposition | KAOS-style AND/OR goal structuring |
| north-star-synthesis | Converge into North Star + ResearchBrief |
Default Flow (reference only)
actor-profiling (simplified) → landscape-reconnaissance (simplified or skipped)
→ direction-narrowing → obstacle-analysis → goal-decomposition → north-star-synthesis
This is a reference, not a mandate. How to simplify, how much to simplify, whether to skip entirely — these are your decisions. This strategy suggests simplification as the default posture, but you judge based on what the user's initial message reveals.
Simplification Guidance
- actor-profiling: The user's stated direction already reveals partial context. Focus on resources, constraints, and intentionality rather than exhaustive background exploration.
- landscape-reconnaissance: The user already knows the general field. You may skip broad scanning and go directly to direction-narrowing, or do a targeted scan of the specific sub-area they mentioned.
Iteration Points
- From obstacle-analysis: may return to landscape-reconnaissance, direction-narrowing, or obstacle-analysis itself
- From goal-decomposition: may return to landscape-reconnaissance, direction-narrowing, obstacle-analysis, or goal-decomposition itself
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.
- 8d ago First seen · 68 lines · 73 tokens per session scan A 68cde30e10e6
warm-start is a skill published in the GitHub repository yogsoth-ai/north-star-crystallization (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 694 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to cold-start, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
journal-abbrev
Uma ferramenta para consultar e padronizar abreviações de nomes de revistas e periódicos científicos, incluindo os formatos ISO 4 e MEDLINE. Também trabalha com nomes de periódicos em arquivos BibTeX, usados para referências bibliográficas.
kami-deck
A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
architecture-design
Use only when creating new registrable ML components that require Factory or Registry patterns.
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
ads-launch
Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.