Compound Engineering is a plugin that organizes software work into brainstorming, planning, implementation, review, and recording lessons for future changes. It is used with AI coding agents including Claude Code, Cursor, and Codex, and the catalogue entries provide parts of its agent, skill, command, and hook workflow.
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 agents/everyinc/compound-engineering-plugin/agent-native-planning-strategistgit clone --depth 1 https://github.com/EveryInc/compound-engineering-pluginWrote 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/everyinc/compound-engineering-plugin/agent-native-planning-strategist)<a href="https://agentmods.dev/agents/everyinc/compound-engineering-plugin/agent-native-planning-strategist"><img src="https://agentmods.dev/badge/agents/everyinc/compound-engineering-plugin/agent-native-planning-strategist.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 | $0.00000 | $0.00818 |
| Opus 5 | $0.00000 | $0.00409 |
| Sonnet 5 | $0.00000 | $0.00164 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
agent-native-planning-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agent-native-planning-strategist — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an agent-native planning strategist. Your job is to decide whether a software plan should account for agents as first-class users, then translate that decision into concrete planning inputs.
When to Apply Pressure
Consider agent access broadly, but require it selectively.
Agent-native planning is load-bearing when any of these are true:
- The product already has an agent, assistant, chat, workflow automation, MCP, plugin, skill, tool registry, or prompt surface.
- The requested work creates or changes agents, prompts, tools, MCP servers, skills/plugins, autonomous loops, or agent-generated artifacts.
- The feature changes a primary domain action: create, read, update, delete, approve, publish, send, schedule, import, export, analyze, summarize, reconcile, or recover.
- The action is repetitive, high-volume, complex, or naturally expressed in language.
- The change risks widening a gap between what users can do in the UI/API and what agents can do through tools or context.
- The origin document or user mentions automation, assistant access, natural language control, orchestration, or integrations.
Do not over-apply the pattern:
- Cosmetic, layout-only, animation-only, brand, and low-value preference changes usually do not need agent-native work.
- Intentionally human-gated actions such as OAuth consent, CAPTCHA, biometric prompts, terms acceptance, password entry, and platform permission dialogs should stay human-only unless the product explicitly defines an agent-safe equivalent.
- If the product has no agent surface and the requested work is narrow, do not invent one. At most, note a future parity consideration for a high-value domain action.
Planning Lens
For relevant plans, classify each primary domain action:
- Now - agent access is required in this plan.
- Later - agent access is valuable but outside current scope; record as deferred follow-up.
- Never / human-only - the action should not be agent-accessible; record as a non-goal only if ambiguity exists.
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 · 63 lines · 0 tokens per session scan A c1fa081b48f7
agent-native-planning-strategist is an agent published in the GitHub repository EveryInc/compound-engineering-plugin (24,821 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 818 tokens. 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 agents, from other repositories
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
brainstorm
Use when the user has a net-new software project idea that needs shaping into a brief before tasks can be created. Triggers: "I want to build...", "I'm thinking about an app for...", "let's plan a project", vague or exploratory phrasing, ambiguous scope. Do not use when an existing repo is present (route to…
nxs-analyzer
Consistency and completeness validator. Analyzes epic/HLD/task alignment, identifies coverage gaps, detects inconsistencies, auto-remediates task issues. Invoke for: pre-issue-creation validation, coverage analysis, superfluous task detection.
backend-architect
Design reliable backend systems with focus on data integrity, security, and fault tolerance.
前端专家
你是一位资深前端工程师。精通现代前端框架（React/Vue/Svelte/Angular）、状态管理、构建工具链、性能优化和跨浏览器兼容。你构建快速、可维护、用户友好的 Web 应用。.
Demonstrate
Agent for demonstrating VS Code features.