agentmods.dev

architect

architect is a skill for Claude Code from ryanczak/rexyMCP. It costs 53 tokens per session (6,545 once invoked), scanned A, original, MIT.

A planning skill for the architect/executor workflow used by rexyMCP projects. It prepares a repository and writes documents describing the next work phase, while leaving execution and milestone approval to people.

In plain words
What is it for?
Use it to set up the workflow in a repository, design upcoming work, draft the next phase, or review progress toward a milestone.
Why use it?
It separates design decisions from implementation, so work can be planned and reviewed before an executor changes the code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions .claude-plugin; mentions CLAUDE.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is contract file [REXYMCP.md](../REXYMCP.md) using the `view_file` tool to.

Part of the rexymcp plugin — 5 skills, 1 MCP server shipped together

not rated 85repo changed 1mo ago A scan SkillSpector: warn 53 tokens original MIT

Good fit Use it to set up the workflow in a repository, design upcoming work, draft the next phase, or review progress toward a milestone.

Compare 6 skills from other repositories ↓
View source ↗ ryanczak/rexyMCP
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ryanczak/rexyMCP
agentmods
npx agentmods add skills/ryanczak/rexymcp/architect

Made for: Claude Code.

Or install rexymcp, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/ryanczak/rexymcp/architect/github.svg)](https://agentmods.dev/skills/ryanczak/rexymcp/architect)
Your own site
<a href="https://agentmods.dev/skills/ryanczak/rexymcp/architect"><img src="https://agentmods.dev/badge/skills/ryanczak/rexymcp/architect/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.

agentmods 80×15 button for architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/ryanczak/rexymcp/architect"><img src="https://agentmods.dev/badge/skills/ryanczak/rexymcp/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,545 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 7
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • medium Rogue Agent · line 190
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00053 $0.06545
Opus 5.5 $0.00021 $0.02618
Sonnet 5.5 $0.00011 $0.01309
Haiku 4.5 $0.00005 $0.00654

Measured 1mo ago against content hash c3d2c28383bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architect 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 1mo 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.

plugin/skills/architect/SKILL.md · 501 lines

How it starts

The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Skill

This skill drives the architect/executor split for rexyMCP projects. When invoked via /rexymcp:architect (no args), it bootstraps an uninitialized target repo and then explores and designs. When invoked via /rexymcp:architect next, it drafts the next phase doc. The architect never executes phases, never auto-advances, and never crosses milestone boundaries without human sign-off.

Read these first

Before any action, read the following from the plugin's own resources (not the target repo — those may not exist yet):

  1. <plugin-dir>/templates/STANDARDS.md — the engineering Definition of Done.
  2. <plugin-dir>/templates/WORKFLOW.md — phase lifecycle, status transitions, Update Log templates, the phase-doc template.
  3. docs/architecture.md — the rexyMCP design (this repo).
  4. docs/dev/milestones/M6-plugin/README.md — the active milestone.

The plugin directory is where this skill lives. Templates are at plugin/templates/STANDARDS.md and plugin/templates/WORKFLOW.md relative to the rexyMCP repo root. Once the plugin is installed in a target repo, the templates are at the plugin's install location — use ${CLAUDE_PLUGIN_DIR} / ${ANTIGRAVITY_PLUGIN_DIR} or walk from the skill's own directory (using ${CLAUDE_SKILL_DIR} / ${ANTIGRAVITY_SKILL_DIR} or by parsing the absolute path of this skill file) up to the plugin root, then into templates/.

1. Bootstrap routine (idempotent)

On the first /rexymcp:architect invocation against a target repo that lacks the rexyMCP scaffold, run the three-step bootstrap below. On re-invocation, check each artifact and only fill missing pieces.

Idempotency check

Before any step, check for these four artifacts in the target repo:

  • rexymcp.toml (with a [project] id UUID and all four [commands] fields set)
  • docs/dev/STANDARDS.md
  • docs/dev/WORKFLOW.md
  • REXYMCP.md and either a CLAUDE.md that imports it (@REXYMCP.md) or a .agents/AGENTS.md referencing it

Read the full file on GitHub · 501 lines

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. 1mo ago Changed · -42 lines c3d2c28383bb
  2. 1mo ago Changed · +7 lines 1de91ecbc104
  3. 2mo ago First seen · 536 lines · 53 tokens per session scan A 61ebe0177d89

Subscribe to this mod's changes

architect is a skill published in the GitHub repository ryanczak/rexyMCP (85 stars, last pushed 12d ago), licensed MIT. It adds 53 tokens to every session and 6,545 once invoked, about $0.0002 per session on Opus 5.5. 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.

Planning
Related

architect compared with skills from other repositories

architect next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
architectryanczak/rexyMCPSkill8512d agoMITA53Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code