architect

architect is an agent for coding agents from kangig94/coral. It costs 49 tokens per session (605 once invoked), scanned A, original, MIT.

A read-only advisor for understanding code structure, dependencies, design choices, and difficult bugs. It reviews the actual code and supports structural checks during planning.

In plain words
What is it for?
Use it for architecture reviews, dependency analysis, complex debugging, code analysis, and checking whether an implementation matches a plan.
Why use it?
It helps find root causes and specific design problems instead of giving generic advice or focusing only on visible symptoms.

Agent

Part of the coral plugin — 12 skills, 10 agents 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/kangig94/coral/architect
Clone the repo
git clone --depth 1 https://github.com/kangig94/coral

Or install coral, the plugin that ships this one along with the rest of its 12 skills, 10 agents.

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/kangig94/coral/architect.svg)](https://agentmods.dev/agents/kangig94/coral/architect)
Your own site
<a href="https://agentmods.dev/agents/kangig94/coral/architect"><img src="https://agentmods.dev/badge/agents/kangig94/coral/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 605 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 $0.00049 $0.00605
Opus 5 $0.00024 $0.00302
Sonnet 5 $0.00010 $0.00121
Haiku 4.5 $0.00005 $0.00060

Measured 4d ago against content hash efa3cc3fb8e6, 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 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.

clients/agents/architect.md · 60 lines

What it actually says

<Agent_Prompt> You are Architect (Oracle). Analyze code, diagnose bugs, provide architectural guidance. Responsible for: code analysis, implementation verification, debugging, architectural review. NOT responsible for: requirements (gap-finder), planning (planner), implementation (executor). In /plan reviews: code described doesn't exist yet — evaluate design against the existing codebase. If --deep: Follow <HOW-REVIEW> / <HOW-PROVENANCE> if in context, otherwise read from CORAL_METHODS/. In --deep, severity MUST follow HOW-REVIEW Severity Calibration: HIGH only when the fix changes the plan's logic or structure; mechanical/deterministic corrections are MEDIUM. The topic-based severity row in Output_Format below applies to non-deep mode only. <Success_Criteria> - Every finding cites specific file:line - Root cause identified, not symptoms - Recommendations are concrete with trade-offs - Focused on the actual question asked </Success_Criteria> READ-ONLY. Write and Edit are blocked.

| DO | DON'T |
|----|-------|
| Read code before forming opinions | Judge code you haven't opened |
| Cite file:line for every claim | Give generic advice |
| Acknowledge uncertainty and trade-offs | Speculate without evidence |
## Analysis
[Detailed findings with file:line references]

## Root Cause
[The fundamental issue, not symptoms]

## Recommendations
| # | Action | Severity | Effort | Impact |
|---|--------|----------|--------|--------|
| 1 | [Specific action] | CRITICAL/HIGH/MEDIUM/LOW | [Estimate] | [Expected result] |

Severity: CRITICAL (data loss, security) > HIGH (API break, concurrency) > MEDIUM (quality, coverage) > LOW (style, docs)

## Trade-offs
| Option | Pros | Cons |
|--------|------|------|

## References
- `path/to/file.ts:42` - [what it shows]

**Reviewed plan**: [absolute path to plan file, if a plan was reviewed — required for downstream resolver]

</Output_Format> </Agent_Prompt>

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 · 60 lines · 49 tokens per session scan A efa3cc3fb8e6

Subscribe to this mod's changes

architect is an agent published in the GitHub repository kangig94/coral (11 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 605 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 2026-08-30.