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 agentmods add skills/leanos-technologies/strategy-os/stg-scoring-problemsnpx skills add LeanOS-Technologies/strategy-os --skill stg-scoring-problemsgit 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-scoring-problems)<a href="https://agentmods.dev/skills/leanos-technologies/strategy-os/stg-scoring-problems"><img src="https://agentmods.dev/badge/skills/leanos-technologies/strategy-os/stg-scoring-problems.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 | $0.00042 | $0.01609 |
| Opus 5 | $0.00021 | $0.00805 |
| Sonnet 5 | $0.00008 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
stg-scoring-problems 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 5d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Problem Scoring
Score problem candidates using four-property framework with compression-model elimination. Every score carries a tier label and cited evidence. Output is a problem hypothesis, not a canvas section.
Procedure
Step 1: Load Context [S]
Read: segment hypothesis (or candidates if segment not yet finalized), governor's problem space description, research signals from BUILD phase 1.
Produce: problem generation parameters anchored to segment.
Gate: context_loaded: bool -- segment context and problem space available.
- Pass: Step 2.
- Fail: Report missing inputs. If no segment data, proceed with governor input alone, noting reduced confidence.
Step 2: Enumerate Candidate Problems (Minimum 5) [K-grounded]
Grounded in: segment context, governor's problem description, research signals.
For the target segment, identify 5-7 candidate problems from:
- Governor input (what they believe the problem is)
- Public signals (forums, reviews, job postings, support tickets)
- Competitive analysis (what alternatives solve -- implies the problem)
- Adjacent segment patterns (problems common in related segments)
WebSearch for segment-specific pain signals.
Produce: candidate problem list.
Gate: candidates_enumerated: bool -- at least 5 candidates identified from at least 2 different sources.
- Pass: Step 3.
- Fail: If fewer than 5, broaden search to adjacent problem categories. If still <5, document the search strategy used and proceed with available candidates.
Step 3: Score Each Problem on Four Properties [R]
For each problem, score:
Frequency (1-5):
| Score | Meaning | Evidence Type |
|---|---|---|
| 5 | Multiple times daily | T1 if from workflow analysis; T2 if inferred |
| 4 | Daily | Cite: job descriptions mentioning task, forum post frequency |
| 3 | Weekly | |
| 2 | Monthly | |
| 1 | Rarely |
Severity (1-5):
| Score | Meaning | Evidence Type |
|---|---|---|
| 5 | Business stops | T2 from public signals; T3 for actual pain intensity |
| 4 | Significant loss | Cite: quantified cost (time, money, risk) if available |
| 3 | Notable pain | Qualitative signal if no quantification |
| 2 | Mild annoyance | |
| 1 | Trivial |
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.
- 5d ago First seen · 148 lines · 42 tokens per session scan A b82a8f9947a0
stg-scoring-problems is a skill published in the GitHub repository LeanOS-Technologies/strategy-os (37 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 1,609 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
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.
gepetto
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
crewai
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.