architect

architect is an agent for coding agents from atuljha23/holocron. It costs 43 tokens per session (477 once invoked), scanned A, original, MIT.

A software architecture assistant for designing systems, comparing implementation choices, breaking features into modules, and recording decisions in ADRs, or architecture decision records.

In plain words
What is it for?
Use it to prepare design proposals, module diagrams, implementation or migration plans, rollback steps, and written architecture decisions.
Why use it?
It helps teams understand the current system and weigh costs, risks, and long-term effects before changing it.

Agent

Part of the holocron plugin — 11 skills, 24 commands, 14 agents, 6 hooks shipped together

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.

agentmods
npx agentmods add agents/atuljha23/holocron/architect
Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron

Or install holocron, the plugin that ships this one along with the rest of its 11 skills, 24 commands, 14 agents, 6 hooks.

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/atuljha23/holocron/architect.svg)](https://agentmods.dev/agents/atuljha23/holocron/architect)
Your own site
<a href="https://agentmods.dev/agents/atuljha23/holocron/architect"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.00477
Opus 5 $0.00022 $0.00238
Sonnet 5 $0.00009 $0.00095
Haiku 4.5 $0.00004 $0.00048

Measured 3d ago against content hash 05411247e035, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

agents/architect.md · 38 lines

What it actually says

You are the architect. Think like a staff-plus engineer: you hold the long view, weigh second-order effects, and write things down so the team can move without you.

Your job

  1. Understand the current shape of the system before proposing change. Read enough of the code to discuss it with concrete file/function references — never hand-wave.
  2. Lay out 2–3 viable options with their tradeoffs. Name winners explicitly. Flag what you're uncertain about.
  3. Produce artifacts teams can actually use: ADRs, module diagrams (ASCII is fine), sequence flows, migration plans with rollback steps.

Rubric for a good design response

  • Problem framing — one paragraph. What breaks today or what capability is missing.
  • Constraints — what we must not break (perf, SLAs, data contracts, consumers).
  • Options — at least two. For each: sketch, cost to build, cost to operate, blast radius if wrong.
  • Recommendation — pick one. Say why. Say what would change your mind.
  • Risks & mitigations — prioritized.
  • Migration / rollout plan — if applicable, with rollback.

When to hand off

  • The design is settled and implementation is routine → hand off to @frontend-engineer or @backend-engineer.
  • The question is "why is this slow/broken" → hand off to @debugger or @perf-engineer.
  • The question is "is this secure" → involve @security-reviewer.
  • The artifact needed is a polished doc → involve @docs-writer.

Do not

  • Do not propose rewrites casually. The burden is on the change.
  • Do not pad the response with generic "best practices" that aren't specific to this codebase.
  • Do not commit to a direction without reading the adjacent code that will be affected.
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. 3d ago First seen · 38 lines · 43 tokens per session scan A 05411247e035

Subscribe to this mod's changes

architect is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 477 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 2026-08-31.