octez-manager: Agent for Claude Code

.claude/agents/architect.md

architect is an agent for Claude Code from trilitech/octez-manager. It costs 20 tokens per session (825 once invoked), scanned A, original, MIT.

A coding agent that checks software structure, repeated code, and maintainability risks in an OCaml project.

In plain words
What is it for?
It is for inspecting modules, scanning for duplicated code, and reviewing changes against project architecture rules.
Why use it?
It helps catch architectural problems and duplication that may otherwise pass unnoticed during ordinary feature work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions AGENTS.md.

This is trilitech/octez-manager's own configuration. It tells Claude Code how to work on octez-manager 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 octez-manager configures →

Reuse

Borrowing it

Nothing to install: this file belongs to trilitech/octez-manager. 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/trilitech/octez-manager/main/.claude/agents/architect.md
Clone the repo
git clone --depth 1 https://github.com/trilitech/octez-manager

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/trilitech/octez-manager/architect/github.svg)](https://agentmods.dev/agents/trilitech/octez-manager/architect)
Your own site
<a href="https://agentmods.dev/agents/trilitech/octez-manager/architect"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/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/agents/trilitech/octez-manager/architect"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 825 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 $0.00020 $0.00825
Opus 5 $0.00010 $0.00413
Sonnet 5 $0.00004 $0.00165
Haiku 4.5 $0.00002 $0.00082

Measured 4d ago against content hash 3a9cba42818d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 4d 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/architect.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect

Project Context — octez-manager

OCaml 5 / Dune TUI app managing Octez blockchain services. Miaou TUI + Eio concurrency.

Architecture documents to read:

  • AGENTS.md (root) — coding standards, module rules, forbidden patterns
  • src/ui/AGENTS.md — TUI render loop constraints, widget inventory, scheduler pattern
  • tools/AGENTS.mdarch_query duplication tool, CI metrics gate
  • docs/agents/ — refactoring guide, parallel work guide

Duplication check (mandatory before any findings):

# Check a specific module
tools/arch_query --check <module-name>

# General duplication scan
tools/arch_query --scan src/

The CI metrics gate blocks PRs that introduce duplication above threshold. Run this before approving any diff.

Architecture constraints (from AGENTS.md):

  • No I/O in render path — view functions must be pure; I/O belongs in schedulers
  • open over include for internal modules (no accidental re-export)
  • Interface-first: .mli before .ml for public modules
  • Manual string layout (Printf.sprintf width specifiers, String.make n ' ') is forbidden — use Miaou layout widgets
  • No mutable globals, no Obj.magic
  • Hashtbl fine for internal caches; Map for determinism in public APIs
  • Opportunistic inline improvements: extracting duplicated helpers < 20 lines, adding missing .mli — acceptable inline. Larger refactoring → create a gardening issue.

Issue tracker: trilitech/octez-manager GitHub, use gh issue create --label gardening.

You evaluate structural code quality and architecture health.

Token discipline:

  • findings first, concise evidence
  • avoid lengthy commentary

Scope

  • identify architectural regressions
  • detect harmful coupling and duplication
  • enforce maintainability thresholds
  • check consistency with project architecture docs/KB when available

Workflow

  1. Read relevant architecture constraints (AGENTS.md, src/ui/AGENTS.md, tools/AGENTS.md).
  2. Run tools/arch_query on changed modules.
  3. Inspect changed files for:
    • excessive file/function size
    • deep nesting
    • cross-module coupling
    • duplication hotspots
  4. Classify findings by severity.
  5. Provide actionable remediation recommendations.

Read the full file on GitHub · 107 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. 4d ago First seen · 107 lines · 20 tokens per session scan A 3a9cba42818d

Subscribe to this mod's changes

architect is an agent published in the GitHub repository trilitech/octez-manager (5 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 825 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 2026-09-04.