About octopus-architecture
octopus-architecture is a Codex CLI skill for evidence-based architecture reviews. It examines implementation, callers, tests, change history, and failure behavior to propose an interface, compare design alternatives, and state a decision without authorizing automatic refactoring.
Key features
- 01Evidence-based architecture review
- 02Inspect callers, tests, and source history
- 03Compare two design alternatives
- 04Define migration and test impact
- 05Optional bounded independent review
Use cases
- 01Review a proposed module boundary
- 02Assess a simplification against callers and tests
- 03Compare designs for a demonstrated extension
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ nyldn/ claude-octopus --skill octopus-architectureAfter installing, type/octopus-architecturein Claude Code to confirm it loaded.
Bundled filesagents/openai.yaml
Details
From the project READMEHost: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than
/octo:*slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, seeskills/blocks/codex-host-adapter.md.
Architecture review
Load skills/blocks/engineering-method-selection.md from the installed plugin
and apply only the methods relevant to this task. Preserve this entry point's
execution contract and output format. Read referenced skills as instructions;
do not invoke the current command recursively or add provider calls from a seat.
Run this method on the current host. A routine architecture review makes zero additional provider dispatches.
--peer-review, an explicit independent-review
request, or an existing risk policy may add one bounded external reviewer through
Octopus routing. Report incomplete independent coverage if that reviewer cannot
read the source or does not return a grounded contribution.
Method
Read and apply skills/blocks/architecture-simplification.md from the installed
plugin root. Pin the source revision and inspect implementation, callers, tests,
recent churn, and failure behavior before recommending a boundary.
For a single simplification, produce one evidence-backed interface. For a design choice, produce two alternatives from the same immutable requirements:
- Draft A minimizes caller knowledge and configuration.
- Draft B makes the next demonstrated extension easier.
Label two host-generated drafts as correlated alternatives from one model. If an independent reviewer is authorized, send it the same source and requirements but not Draft A before its first response. Transport diversity does not prove model family diversity. Unknown family means unknown independence.
Completion
Return Evidence, Caller contract, Proposed interface, Migration, Test impact, and Decision. The decision is keep, simplify, or investigate.
simplify requires exact source evidence and a concrete caller example. A design
review never authorizes an automatic refactor.
LSP Integration
When the host exposes language-server tools, use document symbols, workspace symbols, definitions, and references to confirm module boundaries and caller relationships before proposing an interface. Treat LSP results as an index: verify consequential claims against source and tests, and fall back to repository search when the language server is unavailable or incomplete.
Adapted from codebase-design and DESIGN-IT-TWICE in mattpocock/skills at
commit 3cca18b368ae95cdbdebbff572ccafa662551015 under the MIT License. See
THIRD_PARTY_NOTICES.md.