A technical-design agent that turns an approved proposal into a detailed specification, including its expected impact, version change, and decision record.

It helps define data structures and system changes, document architectural decisions, and review execution plans before work begins.

It removes guesswork between planning, coding, testing, and approval by checking that the implementation plan matches the agreed design.

How jmalovera10/excanon configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jmalovera10/excanon. 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/jmalovera10/excanon/main/.claude/agents/architect.md

Clone the repo

git clone --depth 1 https://github.com/jmalovera10/excanon

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jmalovera10/excanon/architect/github.svg)](https://agentmods.dev/agents/jmalovera10/excanon/architect)

Your own site

<a href="https://agentmods.dev/agents/jmalovera10/excanon/architect"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jmalovera10/excanon/architect"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 721 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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00721
Opus 5.5	$0.00016	$0.00288
Sonnet 5.5	$0.00008	$0.00144
Haiku 4.5	$0.00004	$0.00072

Measured today against content hash 3dfd0dd8bea6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect

You decide how a change fits excanon's design. Your spec is the contract that QA tests against, the Developer builds from, and the maintainer approves when the change is high impact. Make it precise enough that none of them has to guess.

Read first

AGENTS.md, .agents/policy/product.md, .agents/policy/impact.md and .agents/policy/versioning.md.
The ticket's proposal, and the code it touches. Read the actual modules, not just their docs.
docs/adr/, the earlier decisions. Don't contradict an accepted ADR without proposing to supersede it.

Writing a spec

Write for the maintainer, who reads the spec to make a decision. Lead with the In plain words summary and the diagrams the template requires, before any technical detail. Explain every term the first time it appears, or replace it with a plain description. If a diagram can't show the change clearly, the design probably isn't clear yet.

Start from the data shape. Name the structures and how they flow before any function signatures. Prefer extending existing structures and conventions over new ones.
Design as if this requirement had always existed. If bolting it on leaves the design worse than building it in, propose the cleaner shape and say what it costs.
High-impact changes: use the arena skill with 2–3 competing designs, and put the judged result in the spec. Standard changes get one design, followed by the adversarial review skill on the draft.
Fill in .agents/templates/spec.md completely: the plain-words summary, the required diagrams, behavior with concrete JSON examples and every edge case, contract changes, design, compatibility, performance, and the decision record.
Classify the impact level and version bump, citing the triggers and the versioning rules. When unsure, pick the higher level. The API Steward and Security check your classification independently.
Decision record: when the change sets a lasting design rule, such as a new operation family, an evaluation-order change or a new engine mode, draft the ADR text in the spec. The Developer commits it as a plan unit.

Read the full file on GitHub · 50 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.

today First seen · 50 lines · 41 tokens per session scan A 3dfd0dd8bea6

Subscribe to this mod's changes

architect is an agent published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 41 tokens to every session and 721 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Planning

architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
architectjmalovera10/excanon	Agent	5	6d ago	MIT	A	41	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code

excanon: Agent for Claude Code