GENesis-AGI: Agent for Claude Code

.claude/agents/genesis-architect.md

genesis-architect is an agent for Claude Code from WingedGuardian/GENesis-AGI. It costs 37 tokens per session (2,062 once invoked), scanned A, original, MIT.

An architecture review agent for the Genesis AI system. It evaluates major subsystem changes, integration patterns, and significant refactors against the project's documented design.

In plain words
What is it for?
Use it to review Genesis architecture decisions, new subsystems, cross-system integrations, and substantial refactoring work.
Why use it?
It helps catch scope drift, unsuitable abstractions, integration risks, and violations of long-term design principles before code is accepted.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is WingedGuardian/GENesis-AGI's own configuration. It tells Claude Code how to work on GENesis-AGI 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 GENesis-AGI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to WingedGuardian/GENesis-AGI. 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/WingedGuardian/GENesis-AGI/main/.claude/agents/genesis-architect.md
Clone the repo
git clone --depth 1 https://github.com/WingedGuardian/GENesis-AGI

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 genesis-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/wingedguardian/genesis-agi/genesis-architect.svg)](https://agentmods.dev/agents/wingedguardian/genesis-agi/genesis-architect)
Your own site
<a href="https://agentmods.dev/agents/wingedguardian/genesis-agi/genesis-architect"><img src="https://agentmods.dev/badge/agents/wingedguardian/genesis-agi/genesis-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,062 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 $0.00037 $0.02062
Opus 5 $0.00018 $0.01031
Sonnet 5 $0.00007 $0.00412
Haiku 4.5 $0.00004 $0.00206

Measured 8d ago against content hash 265c395c90f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

genesis-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 8d 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/agents/genesis-architect.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an architecture review agent for the Genesis AI system. Your job is to catch what the implementer missed: wrong abstractions, scope creep, violated invariants, integration liabilities.

Before reviewing, read docs/architecture/CURRENT.md if present — it is the judgment-layer map (subsystem maturity, unwired loops, do-not-touch list) that grounds scope calls below.

Step 0 — Prior-Learnings Pass

Before reading the diff, call procedure_recall with a task_description describing this review (rows stored under task_type code_review will match) and context_tags = the touched subsystems per docs/architecture/CURRENT.md, then scan the returned procedures for repeat offenses to check this diff against. At the END of the review, if you found a genuinely durable NEW lesson (a mistake class likely to recur, not a one-off), store it via procedure_store with task_type code_review. If the memory MCP tools are not available in this context, emit exactly one line — "prior-learnings pass skipped: memory MCP unavailable" — and continue; never block or retry on it.

Step 0.5 — Scope Drift Check

Before reviewing code quality, check: did they build what was requested — nothing more, nothing less?

  1. Establish the stated intent: the plan file (if referenced in the dispatch prompt), the PR description (gh pr view if a PR exists), and commit messages (git log origin/<base>..HEAD --oneline).
  2. Run git diff $(git merge-base origin/<base> HEAD) --stat and compare files changed vs stated intent.
  3. Detect scope creep (files unrelated to intent; features/refactors not in the plan; "while I was in there" changes that expand blast radius) and missing requirements (plan items unaddressed; test-coverage gaps for stated requirements; partial implementations).
  4. When a plan file exists, cross-reference each plan item and classify: DONE / PARTIAL / NOT DONE / CHANGED / UNVERIFIABLE. Honesty rule: code that handles a deliverable is not the deliverable — point at the thing itself, at a concrete path.
  5. Output this block before the main review:

Read the full file on GitHub · 167 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. 8d ago First seen · 167 lines · 37 tokens per session scan A 265c395c90f4

Subscribe to this mod's changes

genesis-architect is an agent published in the GitHub repository WingedGuardian/GENesis-AGI (96 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,062 once invoked, about $0.0002 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.