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 ntaffzii/Skill-Agents --skill architecture-reviewgit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/architecture-review)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/architecture-review"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/architecture-review/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/ntaffzii/skill-agents/architecture-review"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/architecture-review.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 | $0.00052 | $0.00350 |
| Opus 5 | $0.00026 | $0.00175 |
| Sonnet 5 | $0.00010 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
architecture-review 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 10d 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
Architecture Review
Use this skill to reason about structure before proposing broad changes.
Workflow
-
Map the system
- Identify the relevant modules, entry points, data flow, and ownership boundaries.
- Read local docs, domain glossary, ADRs, and tests if present.
-
Locate design pressure
- Look for repeated conditionals, hidden coupling, unclear ownership, duplicated concepts, awkward test seams, and high-change files.
- Distinguish annoying code from code that blocks future work.
-
Name the domain concepts
- Use existing project language when available.
- Flag mismatches where code names do not match business or product concepts.
-
Propose changes
- Prefer small boundary improvements over sweeping rewrites.
- Give options when tradeoffs are meaningful.
- Identify the first reversible step.
-
Validate
- Explain what tests or probes would prove the architecture change preserved behavior.
- Avoid recommending refactors without a verification path.
Output Format
Current Shape
What the code is doing now.
Pressure Points
Specific issues with file references.
Recommended Move
The smallest valuable design improvement.
Validation
How to prove the change is safe.
Rules
- Do not propose a rewrite unless incremental steps are impossible.
- Do not introduce abstractions just because two blocks look similar.
- Prefer deeper modules with simple interfaces over shallow layers that move complexity around.
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.
- 10d ago First seen · 54 lines · 52 tokens per session scan A 1b9719ff5782
architecture-review is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 350 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
red-team-review
Unified adversarial review: v4.3 Strategic Matrix (MTA-004). 7-phase framework: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA Decision Engine → Blind Spot/Kill Switch → Executive Summary. Absorbs: bias-detector.
decision-journal
Unified decision lifecycle: Pre-decision logging, post-decision review, failure classification, and calibration tracking. Absorbs: post-mortem-engine.
conductor-review
Reviews a completed track against its plan and guidelines; auto-archives on pass, auto-deletes and restarts on fail.
dev-loop
Research → Execute → Dual-Review Loop (Code Quality + Issue Resolution) bis beide Reviews bestanden.
review-loop
Iterative code review — fix P1+P2 until clean, report P3 as an offer.
critical-review
Radical-honesty architectural review — questions code, methodology, design, and operational fitness.