zyrax-guard: Command for Claude Code

.claude/commands/plan.md

plan is a command for Claude Code from tiagosilva07/zyrax-guard. It costs 19 tokens per session (439 once invoked), scanned A, original, MIT.

A planning command that first examines a software request before implementation starts.

In plain words
What is it for?
It is for planning complex development tasks, including architecture decisions, maintainability checks, and task assignment.
Why use it?
It helps clarify assumptions, identify risks, choose an approach, and divide work among specialist agents before code is written.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents.

This is tiagosilva07/zyrax-guard's own configuration. It tells Claude Code how to work on zyrax-guard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zyrax-guard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tiagosilva07/zyrax-guard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tiagosilva07/zyrax-guard/main/.claude/commands/plan.md
Clone the repo
git clone --depth 1 https://github.com/tiagosilva07/zyrax-guard

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 plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/tiagosilva07/zyrax-guard/plan.svg)](https://agentmods.dev/commands/tiagosilva07/zyrax-guard/plan)
Your own site
<a href="https://agentmods.dev/commands/tiagosilva07/zyrax-guard/plan"><img src="https://agentmods.dev/badge/commands/tiagosilva07/zyrax-guard/plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 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 $0.00019 $0.00439
Opus 5 $0.00010 $0.00219
Sonnet 5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 7d ago against content hash c62390a438a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

plan 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.

.claude/commands/plan.md · 46 lines

What it actually says

You are acting as the technical lead for this request:

$ARGUMENTS

Do NOT start writing implementation code yet. First run a planning pass like a senior lead responsible for maintaining this product for the next five years.

1. Clarify

Restate the goal in your own words. List any assumptions you're making. If something is genuinely ambiguous or a decision has long-term consequences, ask the user before proceeding — one or two sharp questions, not a survey.

2. Challenge

Briefly stress-test the request. Are there scaling, security, or maintainability risks in the obvious approach? Is there a simpler path? Say so now, not after it's built.

3. Decide

State the recommended approach and the key tradeoffs (what you chose, what you rejected, why). Prefer the simplest thing that can scale, and reversible decisions over one-way doors.

4. Route

Break the work into steps and assign each to the right specialist. Delegate by invoking these subagents (each runs in its own context — pass it the files, errors, and decisions it needs, since it can't see this conversation):

  • architect — system/API/schema design for new features or services
  • refactorer — restructure/clean up existing code without changing behavior
  • debugger — root-cause a bug or failure
  • perf-optimizer — fix a measured performance/scale problem
  • security-auditor — read-only security review (use before shipping sensitive code)
  • devops — deployment, CI/CD, monitoring

Relevant skills (clean-architecture, accessible-components, production-readiness) will load automatically when they apply.

5. Plan output

Produce a short, ordered implementation plan: each step, who does it (which agent or the main session), and what "done" looks like. Note what's deferred and why.

Then stop and let the user confirm or adjust before execution begins.

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 · 46 lines · 19 tokens per session scan A c62390a438a5

Subscribe to this mod's changes

plan is a command published in the GitHub repository tiagosilva07/zyrax-guard (2 stars, last pushed 26d ago), licensed MIT. It adds 19 tokens to every session and 439 once invoked, about $0.0001 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 2026-08-31.