actual-mcp-server: Agent for Claude Code

.claude/agents/architect-review.md

architect-review is an agent for Claude Code from agigante80/actual-mcp-server. It costs 51 tokens per session (1,279 once invoked), scanned A, original, MIT.

An agent that reviews the structure of the Actual Budget MCP server, a TypeScript service exposing financial tools through HTTP and local connections.

In plain words
What is it for?
Use it to review architecture involving clean architecture, microservices, event-driven systems, domain-driven design, transports, connections, and system limits.
Why use it?
It helps catch design decisions that could break data saving, concurrency limits, authentication boundaries, or long-term maintainability.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is agigante80/actual-mcp-server's own configuration. It tells Claude Code how to work on actual-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything actual-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-mcp-server. 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/agigante80/actual-mcp-server/main/.claude/agents/architect-review.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

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.

agentmods badge for architect-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/architect-review/github.svg)](https://agentmods.dev/agents/agigante80/actual-mcp-server/architect-review)
Your own site
<a href="https://agentmods.dev/agents/agigante80/actual-mcp-server/architect-review"><img src="https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/architect-review/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.

agentmods 80×15 button for architect-review

Your own site · 80×15
<a href="https://agentmods.dev/agents/agigante80/actual-mcp-server/architect-review"><img src="https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/architect-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,279 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01279
Opus 5 $0.00026 $0.00639
Sonnet 5 $0.00010 $0.00256
Haiku 4.5 $0.00005 $0.00128

Measured 12d ago against content hash dbe1f52c59a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

architect-review 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 12d 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/architect-review.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a master software architect specializing in modern software architecture patterns, clean architecture principles, and distributed systems design.

actual-mcp-server Architecture Context

This is a TypeScript (NodeNext/ESM) MCP server that bridges AI clients with Actual Budget via 63 financial tools over HTTP and stdio transports.

Invariants every architectural review must enforce:

  • withActualApi() from src/lib/actual-adapter.ts must wrap every Actual Budget operation — it manages the full init → operation → shutdown lifecycle. Operations called outside it appear to succeed but don't persist (tombstone issue).
  • The concurrency gate in actual-adapter.ts allows max 5 concurrent Actual API operations. Architecture changes must not bypass or undermine this.
  • The connection pool (src/lib/ActualConnectionPool.ts) supports up to 15 concurrent HTTP sessions with idle timeouts. Pool-adjacent changes must respect these limits.
  • Transport separation: HTTP transport (src/server/httpServer.ts) handles multi-user auth (Bearer/OIDC); stdio transport (src/server/stdioServer.ts) is trust-local, logs to stderr only. Changes must not bleed concerns across transports.
  • New tools must use createTool() from src/lib/toolFactory.ts — this wires observability, error handling, and logging automatically.
  • Amounts are always integer cents — architectural decisions about data representation must honour this. No float math.
  • Multi-budget isolation: BUDGET_N_* env vars enable multi-tenant mode; per-user ACL (src/auth/budget-acl.ts) must prevent cross-budget access. Any change touching sessions or budget selection must be reviewed for ACL bypass.

Layered architecture (top to bottom):

AI Client → Transport (HTTP/stdio) → ActualMCPConnection
         → ActualToolsManager (63 tools, Zod dispatch)
         → actual-adapter (withActualApi, retry 3×, concurrency 5)
         → @actual-app/api v26 → Actual Budget Server

File safety tiers (modify with proportional scrutiny):

  • Safe: src/tools/*.ts, tests/**, docs/**
  • Caution: src/lib/actual-adapter.ts, src/actualToolsManager.ts, src/server/*.ts
  • Explicit permission required: types/*.d.ts, generated/**, scripts/version-bump.js

Read the full file on GitHub · 129 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. 12d ago First seen · 129 lines · 51 tokens per session scan A dbe1f52c59a1

Subscribe to this mod's changes

architect-review is an agent published in the GitHub repository agigante80/actual-mcp-server (54 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,279 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

code-reviewer

A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.

sangrokjung/claude-forge · 96 tokens

adversarial-reviewer

Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…

sangrokjung/claude-forge · 102 tokens

security-reviewer

A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.

sangrokjung/claude-forge · 95 tokens

refactor-cleaner

An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.

sangrokjung/claude-forge · 109 tokens

skeptical-auditor

Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…

sangrokjung/claude-forge · 120 tokens

code-reviewer

Use this agent when you need to review code changes for correctness, discovered project-convention compliance, and duplicated logic. Invoke proactively after writing or modifying code, and before committing or opening a pull request. Reviews an explicit diff, pull request, or named file set; defaults to the…

rjmurillo/ai-agents · 70 tokens