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.
curl -O https://raw.githubusercontent.com/tiagosilva07/zyrax-guard/main/.claude/commands/plan.mdgit clone --depth 1 https://github.com/tiagosilva07/zyrax-guardWrote 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/commands/tiagosilva07/zyrax-guard/plan)<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>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 | $0.00019 | $0.00439 |
| Opus 5 | $0.00010 | $0.00219 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
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.
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.
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.
- 7d ago First seen · 46 lines · 19 tokens per session scan A c62390a438a5
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.
Other commands, from other repositories
quality
Run full Fettle quality scan on the current project.
review
Run an independent cross-review of a file using a different LLM.
security-review
Run security-focused review using ruff S-rules and semgrep OWASP patterns.
report
Show effectiveness metrics from Fettle's trace data.
baseline
Manage violation baselines for gradual adoption.
threat-model
Generate a STRIDE-based threat model with auto-populated entry points and data stores.