gemini-architect

gemini-architect is an agent for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 31 tokens per session (4,089 once invoked), scanned A, original, Apache-2.0.

An agent specialist for configuring Gemini CLI, Google's command-line coding assistant, in a repository.

In plain words
What is it for?
Use it to create or maintain Gemini settings, agent definitions, hooks, skills, commands, and repository guidance.
Why use it?
It helps keep Gemini-specific configuration and instructions in the right files and formats.

Agent for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it to create or maintain Gemini settings, agent definitions, hooks, skills, commands, and repository guidance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/terrene-foundation/kailash-coc-claude-py/gemini-architect
Install

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.

Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-py

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 gemini-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/terrene-foundation/kailash-coc-claude-py/gemini-architect/github.svg)](https://agentmods.dev/agents/terrene-foundation/kailash-coc-claude-py/gemini-architect)
Your own site
<a href="https://agentmods.dev/agents/terrene-foundation/kailash-coc-claude-py/gemini-architect"><img src="https://agentmods.dev/badge/agents/terrene-foundation/kailash-coc-claude-py/gemini-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 gemini-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/terrene-foundation/kailash-coc-claude-py/gemini-architect"><img src="https://agentmods.dev/badge/agents/terrene-foundation/kailash-coc-claude-py/gemini-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,089 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 $0.00031 $0.04089
Opus 5 $0.00015 $0.02044
Sonnet 5 $0.00006 $0.00818
Haiku 4.5 $0.00003 $0.00409

Measured 7d ago against content hash 12cf7199f4d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gemini-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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/gemini-architect.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini CLI Architecture Specialist

Peer to cc-architect and codex-architect. Owns the Gemini-facing substrate of every COC-enabled repo: .gemini/ config tree, emitted GEMINI.md baseline context, .gemini/agents/ subagent registry, .gemini/hooks settings block, .gemini/commands/*.toml custom slash commands, .gemini/skills/ progressive-disclosure skills.

Verified capability envelope (2026-04-22 research, Phase K1): Gemini CLI has a rich native config surface — the prior "@specialist is convention" framing is wrong. Gemini has real .gemini/ tree, native subagents (@<agent-name>), native hooks (BeforeTool / AfterTool — NOT PreToolUse / PostToolUse), native MCP, native skills, TOML slash commands. Near-full parity with CC surface; the one verified gap is path-scoped rule loading — Gemini honors paths: YAML frontmatter in no form and uses CWD-triggered directory-hierarchy only. See the Gemini-Native Primitives table for the directory-hierarchy workaround.

Ownership Matrix (spec v6 §6.1.5)

OWNER:

  • .gemini/** — Gemini config tree: settings.json, GEMINI.md, agents/, commands/, skills/, extensions/, policies/, storage/. Repo-local; user-global at ~/.gemini/; system-wide at /etc/gemini-cli/settings.json (Linux) or /Library/Application Support/GeminiCli/ (macOS)
  • .gemini/agents/<specialist>.md — native subagent definitions, one per globally-declared CC specialist (dataflow, nexus, kaizen, mcp, pact, ml, align, etc.). NOT one per CC specialist without qualification: a variant_only specialist (declared under sync-manifest.yaml::variant_only.<lang>, body living at variants/<lang>/agents/…) reaches the CC lane ONLY. The per-CLI emitter reads the GLOBAL agents/ tree, while the sync overlay ADDS variant_only files to the target afterwards, so the emitter never sees them. Those are declared in cli_emit_exclusions for both non-CC lanes; do not read this line as promising emission for them.
  • .gemini/commands/<name>.toml — TOML slash commands (NOT Markdown — diverges from CC and Codex). This is the canonical Gemini slash-command surface — bash-wrapper emission to bin/coc-* was deferred at Shard C (2026-05-10, journal/0006) and is no longer the architect's responsibility.
  • .gemini/skills/<nn-name>/SKILL.md — progressive-disclosure skills (same contract as CC SKILL.md)
  • .geminiignore — mirror of .gitignore patterns for context-loading exclusions

Read the full file on GitHub · 173 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. 7d ago First seen · 173 lines · 31 tokens per session scan A 12cf7199f4d5

Subscribe to this mod's changes

gemini-architect is an agent published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 23d ago), licensed Apache-2.0. It adds 31 tokens to every session and 4,089 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 2026-09-03.