odin

An architecture adviser that examines code and system designs without changing them. It can return structured findings about design quality, security, impacts, legacy code, complexity, and technology choices.

In plain words
What is it for?
Reviewing architectures, assessing security, analysing proposed changes, understanding legacy systems, simplifying complex designs, and comparing technology options.
Why use it?
It gives developers a separate review of important technical decisions before they implement or alter them.

Command

Part of the msft-arch plugin — 29 skills, 4 commands, 2 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 commands/tqnonline/agent-forge/odin
Clone the repo
git clone --depth 1 https://github.com/tqnonline/agent-forge

Or install msft-arch, the plugin that ships this one along with the rest of its 29 skills, 4 commands, 2 agents.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 192 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 $0.00015 $0.00192
Opus 5 $0.00008 $0.00096
Sonnet 5 $0.00003 $0.00038
Haiku 4.5 $0.00002 $0.00019

Measured 2d ago against content hash 3021cfa499f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

odin 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.

plugins/msft-arch/commands/odin.md · 25 lines

What it actually says

Invoke Odin for deep reasoning and expert architecture guidance. Odin analyzes your code and designs without making changes, returning structured advisory output.

Capabilities:

  • Architecture review and design validation
  • Security assessment (STRIDE analysis, threat modeling)
  • Impact analysis for proposed changes
  • Legacy code comprehension
  • Complexity decomposition and simplification
  • Technology decision trade-off analysis

Usage:

/msft-arch:odin Review the architecture in design.md
/msft-arch:odin How should I build a claims processing system?
/msft-arch:odin Simplify this microservice — it has 47 endpoints
/msft-arch:odin Assess the security of our API gateway design

Odin returns a structured analysis (Assessment, Recommendations, Risks, Next Steps) that you or other agents can act upon.

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 · 25 lines · 15 tokens per session scan A 3021cfa499f3

Subscribe to this mod's changes

odin is a command published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 15 tokens to every session and 192 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 2026-08-31.