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 skills add owainlewis/blueprint --skill architecturegit clone --depth 1 https://github.com/owainlewis/blueprintWrote 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.
[](https://agentmods.dev/skills/owainlewis/blueprint/architecture)<a href="https://agentmods.dev/skills/owainlewis/blueprint/architecture"><img src="https://agentmods.dev/badge/skills/owainlewis/blueprint/architecture/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.
<a href="https://agentmods.dev/skills/owainlewis/blueprint/architecture"><img src="https://agentmods.dev/badge/skills/owainlewis/blueprint/architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00642 |
| Opus 5.5 | $0.00021 | $0.00257 |
| Sonnet 5.5 | $0.00010 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
architecture 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture
Fill in this template in root ARCHITECTURE.md. It describes the system you intend to build and stays current as it changes. Product needs go in requirements; one feature's design goes in a spec.
Steps
- Read
REQUIREMENTS.md, the repository instructions, and any existing code, schemas, and infrastructure. Check every claim about the current system against them. - Ask the user about each decision that shapes the system: boundaries, who owns which data, dependencies, and hard limits. Give your recommended answer with each question.
- Choose the simplest design that meets the requirements. For each big decision, name the strongest alternative and why you did not pick it.
- Fill in the template. Render the diagram and check that it matches the text.
- Stop when the document is ready for review. Do not plan tasks or write code.
Template
# <System> architecture
Status: Proposed | Accepted. <What is built today, and what is not yet.>
## Intended system
<Two or three sentences: the main parts and the source of truth.>
```mermaid
flowchart LR
user([User]) -->|request| app[App]
app -->|reads and writes| db[(Database)]
```
<One line on the main flow and any trust boundary the reader must know.>
## Responsibilities
<What each part owns, what it must not own, and which way dependencies point.>
## Data model
<Core entities, how they relate, who owns each, and the rules that keep data consistent.>
## Critical flows
<The flows that matter most, step by step, including failure and retry.
Give each rule every feature must follow an INV-n ID and say how it is checked.>
## Security and operations
<Trust boundaries, who can do what, deployment, monitoring, and recovery.>
## Decisions
| Decision | Chosen | Instead of | Why | Cost |
|---|---|---|---|---|
## Open decisions
<Each unanswered question, your recommended answer, and what it blocks.>
Rules
- Keep existing
INV-nIDs. Never reuse or renumber them. - Mark a decision Accepted only when a human approves it. Accepted is not the same as built.
- Never invent workload or latency numbers. Mark unknown targets as open decisions.
- Update this document when a change moves ownership, data, interfaces, trust boundaries, or deployment.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +23 lines · +9 tokens per session 8adf59817e69
- 20d ago Changed · +1 lines 1df68283512f
- 26d ago Changed · -44 lines · +4 tokens per session 2e01e136b093
- 2mo ago First seen · 97 lines · 39 tokens per session scan A 1cfe9ed95d46
architecture is a skill published in the GitHub repository owainlewis/blueprint (424 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 642 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
build-executor
Execute an active direct request or approved planned change. Native continuous implementation is the default; existing legacy changes retain their recorded contract obligations.
contract-builder
Maintain an execution contract only for an existing legacy change that requires one. New direct/planned changes do not invoke this skill when a contract is absent.
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.
workflow-start
Primary entry point for the spec-superflow state-machine workflow. Invoke only when the user explicitly requests spec-superflow or an active change contains .spec-superflow.yaml and the user asks to continue that change. Generic proposal, specs, design, task, or contract files are not activation signals.
need-explorer
Clarify intent, scope, constraints, and success criteria before artifact creation. Invoke when the request is fuzzy, the user is comparing options, or the workflow needs a stable change definition before writing artifacts.