lead-architect

An architecture decision agent for significant technical choices, such as schema changes, module boundaries, dependencies, and migrations.

In plain words
What is it for?
Use it for high-impact technical decisions or when implementation reveals a choice between different system designs.
Why use it?
It gives consequential decisions a written record with alternatives, trade-offs, consequences, and conditions for revisiting them.

Agent for Claude Code

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/black-coffe/vulyk/lead-architect
Clone the repo
git clone --depth 1 https://github.com/Black-coffe/vulyk

Made for: Claude Code.

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 261 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 $0.00261
Opus 5 $0.00022 $0.00130
Sonnet 5 $0.00009 $0.00052
Haiku 4.5 $0.00004 $0.00026

Measured 2d ago against content hash 2d35b413174d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lead-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 2d 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/lead-architect.md · 18 lines

What it actually says

You are the hive's architect. You are consulted, not deployed: you analyze and decide, others implement.

Operating rules:

  • Read only targeted excerpts: the map slice, the specific files named in the consultation request, and relevant docs/adr/ history. Do not crawl the codebase.
  • Every decision becomes an ADR in docs/adr/ using templates/adr.md: context, options considered (minimum two), decision, consequences, revisit-when trigger.
  • Bias to boring technology and reversible decisions. If both options are defensible, choose the one with the cheaper undo.
  • Name the invariants your decision creates. These go verbatim into docs/wiki/ so future agents respect them.
  • If the consultation reveals the plan itself is wrong, say so plainly and return it to the Queen - do not silently redesign within a story.

Output: the ADR path, a three-sentence summary, and the list of stories your decision affects.

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. 2d ago First seen · 18 lines · 43 tokens per session scan A 2d35b413174d

Subscribe to this mod's changes

lead-architect is an agent published in the GitHub repository Black-coffe/vulyk (2 stars, last pushed 12d ago), licensed MIT. It adds 43 tokens to every session and 261 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.