Borrowing it
Nothing to install: this file belongs to LeanOS-Technologies/strategy-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LeanOS-Technologies/strategy-os/main/.claude/skills/stg-extracting-insights/SKILL.mdgit clone --depth 1 https://github.com/LeanOS-Technologies/strategy-osWrote 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/leanos-technologies/strategy-os/stg-extracting-insights)<a href="https://agentmods.dev/skills/leanos-technologies/strategy-os/stg-extracting-insights"><img src="https://agentmods.dev/badge/skills/leanos-technologies/strategy-os/stg-extracting-insights/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/leanos-technologies/strategy-os/stg-extracting-insights"><img src="https://agentmods.dev/badge/skills/leanos-technologies/strategy-os/stg-extracting-insights.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 | $0.00045 | $0.01445 |
| Opus 5 | $0.00023 | $0.00723 |
| Sonnet 5 | $0.00009 | $0.00289 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
stg-extracting-insights 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Insight Extraction
Process governor-provided expert sources into structured, tier-labeled insights. Every extracted claim carries a tier label and maps to a specific hypothesis. Behavioral vs hypothetical evidence distinction maintained throughout.
Procedure
Step 1: Ingest Source [S]
Read: source URL, file, or transcript (governor-provided).
- If URL: WebFetch to retrieve content.
- If file: Read file content.
- If transcript: Read transcript.
Identify structure (chapters, sections, speakers). Capture metadata: date, author, platform, publication context.
Produce: raw content + metadata.
Gate: source_ingested: bool -- content retrieved, metadata captured (date, author).
- Pass: Step 2.
- Fail: If URL returns error, report to governor. If content is gated/paywalled, report: "Cannot access -- governor must provide content directly."
Step 2: Extract Claims and Frameworks [K-grounded]
Grounded in: raw content from Step 1.
Identify and extract:
| Category | What to Look For | Example |
|---|---|---|
| Frameworks | Mental models, decision structures | "The 4 properties of a good problem" |
| Principles | Universal rules, guidelines | "Never price below 10x the cost of the alternative" |
| Tactics | Specific actions, playbooks | "Use 5-second tests to validate landing page messaging" |
| Data points | Benchmarks, metrics, statistics | "Average PLG conversion rate is 3-5%" |
| Warnings | Anti-patterns, failure modes | "Teams that skip problem validation fail 3x more often" |
For each: state the claim, cite the specific quote or passage (with location/timestamp if applicable), note the context.
Produce: extracted claims list.
Gate: claims_extracted: bool -- at least 3 claims extracted, each with specific citation from source.
- Pass: Step 3.
- Fail: If source is too thin for 3 claims, extract what exists and note: "Source produced limited actionable claims."
Step 3: Tier-Label Each Claim [R]
For each claim, apply the operational test: "What new data would I need to see to change my mind about this?"
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 · 132 lines · 45 tokens per session scan A 31c36bfa3e30
stg-extracting-insights is a skill published in the GitHub repository LeanOS-Technologies/strategy-os (37 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,445 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 2026-08-30.
Other skills, from other repositories
email-sequence
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
content-research-writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA…