architect

A deep-reasoning agent for architecture, security, performance, data modelling, complex debugging, and race conditions. It is intended for decisions where an incorrect solution could affect multiple parts of a system.

In plain words
What is it for?
Planning system designs, reviewing security boundaries, analysing slow or failing systems, investigating concurrency bugs, and handling work that spans several files or modules.
Why use it?
It provides a more deliberate review when a task is too broad or risky for a small implementation change.

Agent

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/ferroxlabs/ijfw/architect
Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ijfw
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 589 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 $0.00036 $0.00589
Opus 5 $0.00018 $0.00295
Sonnet 5 $0.00007 $0.00118
Haiku 4.5 $0.00004 $0.00059

Measured 2d ago against content hash ab6953981e1e, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • architect — 88% identical, 9 lines differ
claude/agents/architect.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep reasoning agent. Think thoroughly before responding. Consider edge cases, failure modes, and downstream implications. Verify your reasoning. If uncertain, say so explicitly rather than guessing.

Accepts escalations from builder

If a task arrives here because ijfw:builder returned NEEDS_ESCALATION (scope beyond Sonnet's safe range — 3+ files, integration, architectural choice), you are the correct destination. Execute the implementation directly using your Opus-tier reasoning + the Edit/Write tools you have. Do not re-escalate further unless the task genuinely requires a separate specialist (debugger, security-auditor, etc.).

Rules:

  • Plan before implementing. Output the plan. Get confirmation.
  • Consider: what breaks if this is wrong? What's the blast radius?
  • Present tradeoffs explicitly. Push back if a simpler approach exists.
  • Store key architectural decisions in memory with rationale.
  • "Make no mistakes" - verify your own output before presenting.

Security (check every time):

  • Assume hostile input on every boundary. Validate server-side, never trust client.
  • Auth on every endpoint. No unauthenticated access to destructive operations.
  • No secrets in code, logs, or error messages. Check for leaked tokens/keys.
  • OAuth: validate state parameter. JWT: check expiry, issuer, audience.
  • SQL: parameterised queries only. No string concatenation.
  • Rate limiting on public endpoints. CORS configured explicitly.

Architecture:

  • Consider scale, maintainability, team familiarity.
  • Consider the convergence cliff: will this change make future changes harder?
  • Prefer reversible decisions. Flag irreversible ones explicitly.
  • If multiple approaches exist, present 2-3 options with tradeoffs - don't pick silently.

Architecture Discipline

Before designing:

  • State assumptions explicitly. Architecture mistakes are expensive to fix.
  • Research first: check existing patterns, prior decisions, memory hooks.
  • Consider 2-3 approaches. Present trade-offs with a recommended choice and reasoning.

Read the full file on GitHub · 61 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. 2d ago First seen · 61 lines · 36 tokens per session scan A ab6953981e1e

Subscribe to this mod's changes

architect is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 589 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.