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 skills/future-cx/ai-architecture-toolkit/write-a-principlenpx skills add Future-CX/AI-Architecture-Toolkit --skill write-a-principlegit clone --depth 1 https://github.com/Future-CX/AI-Architecture-ToolkitWrote 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/future-cx/ai-architecture-toolkit/write-a-principle)<a href="https://agentmods.dev/skills/future-cx/ai-architecture-toolkit/write-a-principle"><img src="https://agentmods.dev/badge/skills/future-cx/ai-architecture-toolkit/write-a-principle.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00058 | $0.01253 |
| Opus 5 | $0.00029 | $0.00626 |
| Sonnet 5 | $0.00012 | $0.00251 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
write-a-principle 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 6d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write A Principle
Quick Start
Always run this skill from a private lab repository where this toolkit is mounted as a submodule, typically toolkit/. Write generated principle documents under the private lab repository's root principles/ folder using the preset template in toolkit/skills/write-a-principle/templates/principle-template.md.
Do not run this skill from the public toolkit repository for generated output. Do not write generated principle files under toolkit/principles/. Run the command from the private lab root, or pass --output-root <private-lab-root>, so output goes to <private-lab-root>/principles/.
If running from a different working directory, explicitly target the private lab root:
python3 toolkit/skills/write-a-principle/scripts/write-principle.py "Data Architecture Principles" \
--category-code DATA \
--intent "Define durable data architecture principles for ownership, quality, governance, and integration." \
--principle "Data ownership must be explicit and aligned to business domains" \
--principle-description "Every important data object must have a named business owner and stewardship model" \
--principle-rationale "Ownership makes data quality, access, lifecycle, and change decisions accountable" \
--principle-consequence "Teams must identify ownership before introducing or changing critical data flows" \
--principle-do "Name the owning domain or team for each critical data object" \
--principle-dont "Treat shared data as ownerless platform inventory" \
--principle "Critical data must have defined quality expectations and stewardship" \
--usage "Use these principles when designing data platforms, integrations, analytics products, and governance processes." \
--output-root <private-lab-root>
Run from the private lab root, this creates principles/data-architecture-principles.md beside toolkit/.
Each generated principle is also added to principles/_principles-list.md using a markdown table with name, description, and last_updated columns. Create _principles-list.md when it does not exist. Keep rows sorted alphabetically by principle name.
What ships with it
3 files 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.
- 6d ago First seen · 141 lines · 58 tokens per session scan A 8d77e7e47ded
write-a-principle is a skill published in the GitHub repository Future-CX/AI-Architecture-Toolkit (5 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 1,253 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…