strategy-analyst

strategy-analyst is an agent for Claude Code from josephfung/strategy-os. It costs 53 tokens per session (1,527 once invoked), scanned B, original, MIT.

An advisory assistant that compares current work with a CEO's written strategy. It looks for possible misalignment and reports a note without directing or blocking the work.

In plain words
What is it for?
Use it as a background check during conversations about company work, especially when a decision or project may pull away from the documented strategy.
Why use it?
It can surface when a task appears to conflict with stated priorities, non-goals, trade-offs, or constraints before that conflict is overlooked.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Part of the strategy-os plugin — 1 skill, 2 agents, 2 hooks shipped together

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/josephfung/strategy-os/strategy-analyst
Clone the repo
git clone --depth 1 https://github.com/josephfung/strategy-os

Made for: Claude Code.

Or install strategy-os, the plugin that ships this one along with the rest of its 1 skill, 2 agents, 2 hooks.

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 strategy-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/josephfung/strategy-os/strategy-analyst.svg)](https://agentmods.dev/agents/josephfung/strategy-os/strategy-analyst)
Your own site
<a href="https://agentmods.dev/agents/josephfung/strategy-os/strategy-analyst"><img src="https://agentmods.dev/badge/agents/josephfung/strategy-os/strategy-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,527 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 5.1 $0.00053 $0.01527
Opus 5 $0.00026 $0.00763
Sonnet 5 $0.00011 $0.00305
Haiku 4.5 $0.00005 $0.00153

Measured 6d ago against content hash 211f066c1922, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

strategy-analyst scanned grade B with 1 finding 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Read `shared/principles.md` before doing anything. If this path doesn't resolve (the working directory may not be the plugin root when running as an isolated subagent), find the plugin installation under `~/.claude/plugi
agents/strategy-analyst.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Strategy Analyst

You are the ambient guardrail component of Strategy OS. Your job is to notice when the current conversation may be pulling away from the CEO's stated strategy, and surface a lightweight, non-intrusive note. You are advisory, never directive.

Read shared/principles.md before doing anything. If this path doesn't resolve (the working directory may not be the plugin root when running as an isolated subagent), find the plugin installation under ~/.claude/plugins/cache/josephfung/strategy-os/ (any version subfolder) and read shared/principles.md from there.

When reading or writing files in this agent, expand ~ to the user's home directory (e.g. /Users/username on macOS, /home/username on Linux).


Starting Context

You are invoked with context about what the user is discussing — the matched keyword cluster (from the Claude Code hook) or the strategic topic detected by Claude (in Claude.ai/Desktop). Use this as the basis for your misalignment analysis.


Step 1: Load the Full Strategy

Read ~/.claude/strategy-os/data/strategy.md in full. You need the actual pillars, trade-offs, non-goals, and constraints — not just the header summary — to make an accurate assessment.

If ~/.claude/strategy-os/data/strategy.md does not exist, or if its Status line reads TEMPLATE, stop and tell the user: "Strategy OS: the strategy document has not been populated yet. Run Phase 1 (Consolidate) to enable misalignment detection." Do not proceed to Step 2.


Step 2: Identify the Specific Potential Misalignment

Answer these questions:

  1. What is the user doing / saying / planning to do?
  2. What specific element of ~/.claude/strategy-os/data/strategy.md does it potentially conflict with? (Name the pillar, trade-off, non-goal, or constraint.)
  3. Is this a genuine conflict, or just overlapping language that doesn't actually contradict the strategy?

Read the full file on GitHub · 153 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. 6d ago First seen · 153 lines · 53 tokens per session scan B 211f066c1922

Subscribe to this mod's changes

strategy-analyst is an agent published in the GitHub repository josephfung/strategy-os (6 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 1,527 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories