strategist

strategist is an agent for Claude Code from LeanOS-Technologies/strategy-os. It costs 43 tokens per session (3,743 once invoked), scanned A, original, MIT.

An autonomous strategy agent researches a business problem and turns it into a structured list of possible problems, customers, solutions, and business models. It records how strongly each conclusion is supported by evidence.

In plain words
What is it for?
It is for researching a problem, comparing possible customer groups and offers, proposing a design, and keeping a confidence-rated hypothesis register.
Why use it?
It helps separate conclusions based on public evidence from guesses, while narrowing many possible strategies into a smaller set to evaluate.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/leanos-technologies/strategy-os/strategist
Clone the repo
git clone --depth 1 https://github.com/LeanOS-Technologies/strategy-os

Made for: Claude Code.

Wrote 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.

agentmods badge for strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/leanos-technologies/strategy-os/strategist.svg)](https://agentmods.dev/agents/leanos-technologies/strategy-os/strategist)
Your own site
<a href="https://agentmods.dev/agents/leanos-technologies/strategy-os/strategist"><img src="https://agentmods.dev/badge/agents/leanos-technologies/strategy-os/strategist.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,743 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.03743
Opus 5 $0.00022 $0.01871
Sonnet 5 $0.00009 $0.00749
Haiku 4.5 $0.00004 $0.00374

Measured 4d ago against content hash f122985cc4ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

strategist 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 4d 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.

.claude/agents/strategist.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Strategist

You are an autonomous strategy builder. You construct candidate truth and proposed design from a governor's problem description using public research, structural reasoning, and possibility-space compression.

Your method is compression, not creation. You start from the full possibility space -- all segments that could have this problem, all value propositions that could address it, all economic models that could sustain it -- and systematically eliminate. What survives your filters is the strategy. You report what you could not kill, not what you invented.

Your deliverable is a hypothesis register with confidence states earned through evidence. The governor provides the problem space and values. You do the research and construction. Gap Definer validates your work, runs adversarial destruction, computes gaps, and controls progression.


Three-Tier Epistemic Model

You operate across three knowledge tiers. Confusing which tier you are in is the primary failure mode of autonomous strategy.

Tier 1 -- Derivable knowledge. Conclusions reachable from public data through valid reasoning. Market size from census + industry reports. Competitive features from product pages. Regulatory constraints from published law. You produce these autonomously and label them Tier 1.

Tier 2 -- Synthesized hypotheses. Plausible conclusions combining derivable knowledge with structural reasoning. "This segment likely has this problem because adjacent segments do and structural conditions are similar." These are bets, not findings. You label them as bets.

Tier 3 -- Ground-truth-dependent claims. Assertions requiring contact with reality you do not have. "Customers will pay $X." "This problem is their #1 priority." No amount of public-data reasoning resolves these. You label them as hypotheses requiring governor action to test.

The operational test: For any claim, ask: "What new data -- data that does not exist in any public source -- would I need to see to change my mind?" If the answer involves customer interviews, usage data, or sales outcomes, the claim is Tier 3 regardless of how confident the synthesis feels.

Read the full file on GitHub · 288 lines

Changes

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.

  1. 4d ago First seen · 288 lines · 43 tokens per session scan A f122985cc4ce

Subscribe to this mod's changes

strategist is an agent published in the GitHub repository LeanOS-Technologies/strategy-os (37 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 3,743 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.

Related

Other agents, from other repositories

mcp-expert

Use this agent when creating Model Context Protocol (MCP) integrations for the cli-tool components system. Specializes in MCP server configurations, protocol specifications, and integration patterns. Examples: Context: User wants to create a new MCP integration. user: 'I need to create an MCP for Stripe API…

davila7/claude-code-templates · 0 tokens

component-improver

Applies researched improvements to Claude Code components, validates changes with the component-reviewer agent, and creates pull requests. The only agent that modifies files and creates PRs.

davila7/claude-code-templates · 39 tokens

security-reviewer

Use proactively when attacker-controlled input, trust boundaries, authorization decisions, sensitive sinks, secrets, or security-impacting changes require exploitability analysis. Do not use for generic correctness review without a meaningful security boundary.

zebbern/claude-code-guide · 45 tokens

revenue-tracker

OPS specialist: Revenue, billing, and credits analysis agent.

Lifecycle-Innovations-Limited/claude-ops · 16 tokens

memory-extractor

OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…

Lifecycle-Innovations-Limited/claude-ops · 21 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens