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 jstoup111/ai-conductor --skill architecture-reviewgit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/architecture-review)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/architecture-review"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/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/jstoup111/ai-conductor/architecture-review"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/architecture-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 135 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- medium Rogue Agent · line 249 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 360 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 372 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 384 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00048 | $0.09144 |
| Opus 5.5 | $0.00019 | $0.03658 |
| Sonnet 5.5 | $0.00010 | $0.01829 |
| Haiku 4.5 | $0.00005 | $0.00914 |
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 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 — 631 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Reviews the design through an architectural lens BEFORE stories are written and before any code. Catches technical infeasibility, hidden complexity, architectural drift, and domain violations early — when they're cheap to fix. This is where the how is resolved (so the PRD stays product-only) and captured as APPROVED ADRs.
Read the Scope boundary: from .docs/track/<slug>.md as binding; preserve the confirmed narrow/comprehensive breadth outcome; do not permit a materially broader expansion beyond it unless the operator confirms before it enters the artifact.
Run after /prd (product track) or /explore (technical track), and BEFORE /stories (adr-2026-06-29-architecture-before-stories-convergent-kickback).
The review's input is the PRD's functional requirements (product) or the explore output + technical
intent (technical) — stories and the plan do not exist yet at this point.
Also invocable at pipeline batch boundaries to verify implementation stays architecturally sound.
Correctness gate: an ADR is the most load-bearing artifact in the flow — everything downstream
builds on it. Apply the /verify-claims protocol before writing any APPROVED ADR: state each
technical claim with a grounded confidence % and its basis (verified vs inferred), surface every
assumption the design rests on, and HARD-BLOCK (operator approval interactive, HALT if autonomous)
on any unconfirmed assumption that would change the decision. Do not record a decision as APPROVED
while it rests on an unconfirmed load-bearing assumption.
Provider-native delegation
When this review delegates exploration or analysis, use the selected host's available subagent facility. Preserve the scope limits, evidence, ADR output, and veto/gate behavior regardless of host. Claude delegation: Claude uses the Agent tool; any Claude model choice is confined to that facility. A Codex-selected run uses its available subagent facility and configured Codex provider policy, without translating Claude model names.
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.
- 6d ago Changed · +1 lines c86f6c37edd1
- 13d ago Changed · +1 lines ef331e8821ee
- 14d ago Changed c5dad2bd2ffe
- 16d ago Changed · +26 lines 9cface4377a5
- 17d ago Changed · +8 lines 3df9f64cfb30
- 23d ago Changed · +12 lines 60acfa316d6e
- 26d ago Changed · +10 lines 65af4cf04751
- 27d ago Changed · +21 lines 66e0c71cfa6f
- 1mo ago Changed · +2 lines cc7b6866a610
- 1mo ago First seen · 550 lines · 48 tokens per session scan A c2a7f2a7dcb4
architecture-review is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 9,144 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.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…