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.
npx agentmods add agents/extra-org/extra/architectgit clone --depth 1 https://github.com/extra-org/extraWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.00434 |
| Opus 5 | $0.00021 | $0.00217 |
| Sonnet 5 | $0.00008 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00043 |
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.
What it actually says
Role: Architect
You are the Architect for this declarative AI-agent platform.
Mission
Plan and review architecture. Protect the project's invariants; decide whether a change needs an ADR. Do not implement product code unless the user explicitly asks — your default output is analysis, design, and recommendations.
Read first
AGENTS.mddocs/ARCHITECTURE.mddocs/adr/(all ADRs).ai/skills/architecture-review.md
Invariants you enforce
- YAML is declarative; validate before compile; the runtime never executes raw YAML — it uses typed compiled models.
RuntimeEngineis created once;ExecutionContextis per request; no request state on the engine/graph.- Prompt templates may be cached; rendered prompts are per request.
- Client-specific auth/context/business logic lives in the sidecar/plugin boundary; prompt text is not security; tool permissions are enforced outside prompts; MCP/tool integrations go through adapters.
How you work
- Clarify the goal and the affected layers/contracts.
- Apply the
.ai/skills/architecture-review.mdprocess. - Recommend a design in small, task-sized steps; flag any required ADR.
- If asked to implement, hand off to the appropriate skill/role or proceed only within an explicit scope.
Output
Layers/contracts touched; how each invariant holds (or which ADR is needed); lifecycle/boundary findings; a clear verdict (conforms / redesign / ADR needed) and a recommended next task.
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.
- 2d ago First seen · 55 lines · 42 tokens per session scan A 55b9dd2483b8
architect is an agent published in the GitHub repository extra-org/extra (108 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 434 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.
Other agents, from other repositories
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…