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 Future-CX/AI-Architecture-Toolkit --skill assess-solutiongit 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/assess-solution)<a href="https://agentmods.dev/skills/future-cx/ai-architecture-toolkit/assess-solution"><img src="https://agentmods.dev/badge/skills/future-cx/ai-architecture-toolkit/assess-solution/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/future-cx/ai-architecture-toolkit/assess-solution"><img src="https://agentmods.dev/badge/skills/future-cx/ai-architecture-toolkit/assess-solution.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.01395 |
| Opus 5.5 | $0.00024 | $0.00558 |
| Sonnet 5.5 | $0.00012 | $0.00279 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
assess-solution 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 2mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess Solution
Quick Start
Run an interview-based assessment of a proposed or existing solution against:
- The architecture principles available in
principles/. - One user-selected baseline:
- A capability overview under
capabilities/<slug>/. - A solution architecture design under
solution-architectures/<slug>/.
- A capability overview under
If the user has not identified the capability overview or solution design, ask which one to use before starting the assessment. Use the selected baseline and principles to ask focused questions. Do not produce the final report until the user has answered the interview topics and confirmed that the assessment evidence is complete enough.
Required Inputs
- Solution description, proposal, implementation notes, or path to an existing solution document, gathered or confirmed through the interview.
- Solution supplier, vendor, product company, or implementation partner when the solution depends on an external company.
- Customer references, case studies, testimonials, analyst notes, or reference-call findings when available.
- Assessment baseline: one capability overview or one solution architecture design.
- Architecture principles to assess against. Prefer all principle documents under
principles/unless the user names a subset. - Target audience and desired depth, if different from architecture and delivery stakeholders.
Workflow
- Start in interview mode. Ask one question at a time and do not generate the final assessment until the interview is complete.
- Confirm the solution, supplier, and whether to assess against a capability overview or solution architecture design when the baseline is not explicit.
- Locate and read the selected baseline and architecture principles. If multiple baselines match, ask the user to choose one.
- Extract baseline expectations to build the interview plan:
- Business outcome and scope boundary.
- Main business features or requirements, users, processes, data, integrations, systems, and dependencies.
- Security, privacy, compliance, non-functional, operational, and lifecycle expectations.
- Explicit risks, assumptions, constraints, open questions, and design decisions.
- Interview the user for each main business feature or requirement. Ask for fit, evidence, known gaps, user impact, operational impact, and required action.
- Interview the user on each assessment topic: ease of use, other features, integrations, target architecture alignment, principle alignment, supplier, references, price indication, risks, constraints, and open questions.
- After each topic, summarize captured facts, assumptions, missing evidence, and follow-up questions. Ask follow-ups when answers are vague or unsupported. When there is a strong evidence-based suggestion, include it with the question and ask the user to confirm, correct, or reject it.
- Before writing the report or scorecard, summarize the evidence collected and ask the user to confirm whether to proceed or answer remaining questions.
- Assess principle alignment using
Aligned,Partly aligned,Misaligned, orNot enough evidence. - Create the simple 5-star scorecard only after the interview is complete and the user has confirmed there is enough evidence. Use whole stars only; do not use half-star symbols.
- Identify gaps, risks, trade-offs, and open questions. Do not invent missing facts.
- Give a practical recommendation:
Proceedwhen only minor issues remain.Proceed with conditionswhen risks or gaps need tracked mitigation.Revise before approvalwhen material conflicts or missing decisions remain.Do not proceedwhen the solution conflicts with critical principles or baseline expectations.
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.
- 2mo ago First seen · 80 lines · 60 tokens per session scan A de0c9802a7cc
assess-solution is a skill published in the GitHub repository Future-CX/AI-Architecture-Toolkit (8 stars, last pushed 18d ago), licensed MIT. It adds 60 tokens to every session and 1,395 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 2026-08-31.
assess-solution compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| assess-solutionFuture-CX/AI-Architecture-Toolkit | Skill | 8 | 18d ago | MIT | A | 60 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |