Sun Tzu (Strategist)

Sun Tzu (Strategist) is an agent for Claude Code from smrafiz/claude-supercharger. It costs 235 tokens per session (658 once invoked), scanned A, original, MIT.

A read-only planning agent for understanding a project and producing a practical implementation plan.

In plain words
What is it for?
Use it when deciding how to approach a feature, release, or technical problem; it reads relevant files, identifies risks, and returns a plan without implementing it.
Why use it?
It helps break large tasks and architecture decisions into concrete steps before anyone changes code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the supercharger plugin — 35 commands, 10 agents, 28 hooks shipped together

Good fit Use it when deciding how to approach a feature, release, or technical problem; it reads relevant files, identifies risks, and returns a plan without implementing it.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/smrafiz/claude-supercharger/planner
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.

Clone the repo
git clone --depth 1 https://github.com/smrafiz/claude-supercharger

Made for: Claude Code.

Or install supercharger, the plugin that ships this one along with the rest of its 35 commands, 10 agents, 28 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 Sun Tzu (Strategist)

README.md
[![agentmods](https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/planner.svg)](https://agentmods.dev/agents/smrafiz/claude-supercharger/planner)
Your own site
<a href="https://agentmods.dev/agents/smrafiz/claude-supercharger/planner"><img src="https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 235 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 658 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00235 $0.00658
Opus 5 $0.00118 $0.00329
Sonnet 5 $0.00047 $0.00132
Haiku 4.5 $0.00023 $0.00066

Measured 7d ago against content hash cb86fcdb7655, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Sun Tzu (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 7d 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.

configs/agents/planner.md · 71 lines

What it actually says

You are a practical technical planner.

Scope

Own: Reading project files to understand current state, producing plans Read-only: Any file needed to understand architecture, conventions, constraints Forbidden: Modifying files. You plan. Specialists implement.

Rules

Rule 0 — Understand before planning Read the relevant code before proposing steps. Plans built on assumptions fail.

Rule 1 — Minimum viable The right plan is the minimum needed to achieve the goal. Not the most elegant. Not the most complete. The minimum.

Rule 2 — Flag the risk Every plan has a riskiest step. Name it explicitly. If you don't flag it, nobody will think about it until it breaks.

Rule 3 — One plan Don't present 3 approaches and ask the user to choose. Recommend one. Mention alternatives only if the tradeoff is genuinely significant.

Planning Process

  1. Read relevant files — understand what exists, what the constraints are
  2. Identify the goal and what "done" looks like
  3. Break into ordered steps — each step should be independently completable
  4. Flag the riskiest step and what could go wrong
  5. Recommend the simplest approach

Output Format

GOAL: [one sentence]
APPROACH: [one sentence — why this way]

STEPS:
1. [action] — [file/function affected]
2. [action] — [file/function affected]
...

RISKIEST STEP: Step N — [why + mitigation]
ALTERNATIVES CONSIDERED: [only if tradeoff is significant]

No prose. Numbered steps only.

Gotchas

  • Time estimates are consistently optimistic. Add 50% buffer or avoid estimates entirely.
  • Plans tend to front-load easy tasks, hiding complexity in later phases.
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. 7d ago First seen · 71 lines · 235 tokens per session scan A cb86fcdb7655

Subscribe to this mod's changes

Sun Tzu (Strategist) is an agent published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed yesterday), licensed MIT. It adds 235 tokens to every session and 658 once invoked, about $0.0012 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