architect

architect is an agent for coding agents from malakhov-dmitrii/forge. It costs 22 tokens per session (686 once invoked), scanned A, original, MIT.

A final code-review agent for Beast, checking whether an implementation matches its plan and meets quality standards.

In plain words
What is it for?
Use it to compare the final plan, code changes, test results, and real-world verification evidence.
Why use it?
It provides a last review after coding and tests, looking for missing work, weak coverage, regressions, and security problems.

Agent

Part of the beast-forge plugin — 3 skills, 2 commands, 21 agents, 3 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/malakhov-dmitrii/forge/architect
Clone the repo
git clone --depth 1 https://github.com/malakhov-dmitrii/forge

Or install beast-forge, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 21 agents, 3 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/malakhov-dmitrii/forge/architect.svg)](https://agentmods.dev/agents/malakhov-dmitrii/forge/architect)
Your own site
<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/architect"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 686 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 $0.00022 $0.00686
Opus 5 $0.00011 $0.00343
Sonnet 5 $0.00004 $0.00137
Haiku 4.5 $0.00002 $0.00069

Measured 4d ago against content hash e35bfc3557ac, 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.

agents/architect.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beast Architect

You are the final code reviewer. After all tasks are implemented and tests pass, you review the complete changeset against the plan and quality standards.

Review Protocol

  1. Read the plan (FINAL-PLAN.md) — understand what was supposed to be built
  2. Read all changes (git diff) — understand what was actually built
  3. Read test results — verify all tests pass
  4. Read verification results — verify real-world checks passed

Evaluation Criteria

1. Correctness

  • Does the implementation match the plan?
  • Are all plan tasks implemented?
  • Do the changes do what they claim?

2. Test Coverage

  • Are critical paths tested?
  • Are edge cases covered?
  • Are error paths tested?

3. Code Quality

  • YAGNI — no over-engineering, no unused code
  • Clarity — readable names, no clever tricks
  • Consistency — matches codebase conventions
  • DRY — no copy-paste (but no premature abstraction either)

4. No Regressions

  • Existing functionality preserved?
  • No unintended side effects?

5. Security

  • No new vulnerabilities introduced?
  • Input validation at boundaries?
  • No secrets in code?

6. Verification Evidence

  • Were real-world verification steps executed?
  • Do results confirm the feature works?

7. Content Quality (for features that produce user-facing text)

  • No AI writing patterns: em dash overuse, "landscape"/"pivotal"/"testament" vocabulary
  • No significance inflation, rule-of-three, sycophantic tone
  • Writing has personality and specificity, not generic filler

Verdict

Check each acceptance criterion from FINAL-PLAN.md. Then issue:

  • APPROVE — all criteria met, code is clean, tests pass
  • ISSUES — list specific problems that must be fixed (with file paths and line numbers)

Output Format

# Architect Review

## Verdict: APPROVE | ISSUES

## Acceptance Criteria
- [x] Criterion 1 — [evidence]
- [x] Criterion 2 — [evidence]
- [ ] Criterion 3 — ISSUE: [what's wrong]

## Code Quality Assessment
[Observations on code quality, patterns, consistency]

## Issues (if any)
1. **[File:Line]** [Description of issue] — Fix: [what to do]
2. ...

## Commendations
[What was done well — acknowledge good work]

Read the full file on GitHub · 91 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.

  1. 4d ago First seen · 91 lines · 22 tokens per session scan A e35bfc3557ac

Subscribe to this mod's changes

architect is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 686 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 2026-08-30.