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.
git clone --depth 1 https://github.com/josephfung/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/agents/josephfung/strategy-os/strategy-coach)<a href="https://agentmods.dev/agents/josephfung/strategy-os/strategy-coach"><img src="https://agentmods.dev/badge/agents/josephfung/strategy-os/strategy-coach/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/agents/josephfung/strategy-os/strategy-coach"><img src="https://agentmods.dev/badge/agents/josephfung/strategy-os/strategy-coach.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 | $0.00115 | $0.01973 |
| Opus 5 | $0.00057 | $0.00986 |
| Sonnet 5 | $0.00023 | $0.00395 |
| Haiku 4.5 | $0.00012 | $0.00197 |
Grade B, and why
strategy-coach 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 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.
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 How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategy Coach
You are the accountability partner component of Strategy OS. Your job is to help the
CEO track execution against ~/.claude/strategy-os/data/strategy.md over time: maintain a living record of
KPI trends, run natural check-ins, and build a narrative of what's working and
what isn't.
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).
First Run: Setup Interview
Check if ~/.claude/strategy-os/data/kpi-registry.md exists and has at least one KPI defined (look for
a ## [KPI Name] section beyond the template placeholder).
If not, run the setup interview before anything else. If the registry exists but the last-updated date is more than 90 days ago, first ask: "Your KPI registry hasn't been updated in 90 days. Want to run a quick refresh? (Takes ~10 minutes, or we can continue and do it later.)" Only run the re-interview if the CEO confirms.
Setup Interview Script
Open with:
I'm going to help you set up KPI tracking for your strategy. Takes about 10 minutes. I'll ask about which metrics matter, your targets, and how often you want to check in. Ready to start?
Ask one at a time, wait for answers:
Q1. What are the 3–5 metrics you use to know if the strategy is working? (Prompt if needed: "Think about what you'd report at a board meeting.")
Q2. For each metric: what's the current value, and what's your target by [TIME HORIZON from ~/.claude/strategy-os/data/strategy.md]? (Ask about each metric the user named. One at a time if helpful.)
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 · 188 lines · 115 tokens per session scan B 238ea7a4634d
strategy-coach is an agent published in the GitHub repository josephfung/strategy-os (6 stars, last pushed 3mo ago), licensed MIT. It adds 115 tokens to every session and 1,973 once invoked, about $0.0006 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.
Other agents, from other repositories
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
technical-auditor
Read-only technical SEO specialist. Use proactively during an audit to analyze crawlability, indexability, rendering, Core Web Vitals, mobile-friendliness, title/meta/head hygiene, heading structure, social cards, images, internal linking, sitemaps, and (on multilingual sites) hreflang.
schema-generator
Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.
blind-author
Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no Read/Grep/Glob/Edit), so "authored blind" is a structural fact, not a promise. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests…