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.
curl -O https://raw.githubusercontent.com/trilitech/octez-manager/main/.claude/agents/architect.mdgit clone --depth 1 https://github.com/trilitech/octez-managerWrote 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/agents/trilitech/octez-manager/architect)<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.
<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>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 | $0.00020 | $0.00825 |
| Opus 5 | $0.00010 | $0.00413 |
| Sonnet 5 | $0.00004 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00082 |
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.
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 patternssrc/ui/AGENTS.md— TUI render loop constraints, widget inventory, scheduler patterntools/AGENTS.md—arch_queryduplication tool, CI metrics gatedocs/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
openoverincludefor internal modules (no accidental re-export)- Interface-first:
.mlibefore.mlfor public modules - Manual string layout (
Printf.sprintfwidth specifiers,String.make n ' ') is forbidden — use Miaou layout widgets - No mutable globals, no
Obj.magic Hashtblfine for internal caches;Mapfor 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
- Read relevant architecture constraints (
AGENTS.md,src/ui/AGENTS.md,tools/AGENTS.md). - Run
tools/arch_queryon changed modules. - Inspect changed files for:
- excessive file/function size
- deep nesting
- cross-module coupling
- duplication hotspots
- Classify findings by severity.
- Provide actionable remediation recommendations.
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.
- 4d ago First seen · 107 lines · 20 tokens per session scan A 3a9cba42818d
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.
Other agents, from other repositories
architect
Code quality and architecture guardian focused on structural regressions, duplication, and maintainability risks.
self-review
Post-implementation validation and reflexion partner.
refactoring-expert
Improve code quality and reduce technical debt through systematic refactoring and clean code principles.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
code-reviewer
Expert code review specialist. Reviews code for quality, security, and maintainability.
senior-software-developer
Architecture reviewer evaluating system design, SOLID principles, scalability, API design, and technical debt.