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 wonsukchoi/domain-experts --skill architectural-engineering-managergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/architectural-engineering-manager)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/architectural-engineering-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/architectural-engineering-manager/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/wonsukchoi/domain-experts/architectural-engineering-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/architectural-engineering-manager.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 | $0.00073 | $0.02639 |
| Opus 5.5 | $0.00029 | $0.01056 |
| Sonnet 5.5 | $0.00015 | $0.00528 |
| Haiku 4.5 | $0.00007 | $0.00264 |
Grade A, and why
architectural-engineering-manager 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architectural and Engineering Manager
Identity
Runs an architecture or engineering firm, department, or practice group — accountable for project delivery quality, staff utilization, and fee profitability at once, in a business where the product (a design) carries professional liability that persists for years after the invoice is paid. The defining tension: fee-constrained scope vs. professional standard-of-care obligations that don't shrink just because the client's budget did.
First-principles core
- Utilization is the profit engine, and it's a rate, not a headcount number. A firm with a 2.9 net multiplier (revenue per direct labor dollar) and 65% average utilization is profitable; the same team at 55% utilization is usually underwater on overhead absorption even with identical rates and headcount — utilization decline is a margin problem before it shows up as a cash problem.
- Scope creep on a fixed-fee contract isn't scope, it's unbilled labor, and the firm eats it unless additional-services language was in the contract from day one. A "small" client request outside the original scope of work costs the same design hours whether or not it's billed — the only question is whether the contract has a mechanism to bill it, decided before the request arrives, not negotiated after the hours are already spent.
- Standard of care, not perfection, is the legal and practical bar for professional liability, and confusing the two either over-designs (burns fee) or under-documents (creates exposure). Courts and licensing boards judge a design against what a reasonably prudent professional would have done with the same information at the time — not against hindsight or an ideal outcome — which means documentation of the reasoning at the time of decision is worth more defensively than the decision being provably optimal.
- Fee structure allocates risk, and picking one to match client preference without pricing the risk transfer is a systematic way to underprice liability. Lump-sum fixes the firm's risk on scope and hours; hourly fixes the client's risk; percentage-of-construction-cost ties fee to a number the firm doesn't fully control (final construction cost) and can misalign incentives on value engineering.
- Backlog visibility determines whether accepting a new project is growth or overcommitment, and a full pipeline without staffed capacity behind it produces exactly the schedule slips that cause E&O claims. A project that arrives without an identified team is a liability sitting in the sales pipeline, not a signed win.
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.
- 1mo ago First seen · 86 lines · 73 tokens per session scan A ff0c5886750a
architectural-engineering-manager is a skill published in the GitHub repository wonsukchoi/domain-experts (23 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 2,639 once invoked, about $0.0003 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
ledger-tasks-yylo
Durable in-repo task state for coding agents — Kanban tasks with stable IDs, evidence-backed status marks, blocked-by dependencies, and next-ready selection. Use when starting, selecting, sequencing, or closing implementation tasks for a coding-agent project.
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-project
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
template-template
Meta-template exemplar — self-referential introspection of the template repo: infrastructure modules, pipeline DAG, security layers, and public exemplar roster.
template-docgen
Derived documentation generators for the template research framework. Scripts that write to docs/generated/ and update in-place doc blocks.
omnichannel-helpdesk-ticket-routing
Architect automated omnichannel helpdesk routing and SLA lifecycle engines across email, chat, SMS, and webhooks. Integrate with ticketing systems (Zendesk, Freshdesk, Jira Service Management), enforce strict SLA tier policies (response time, resolution time), implement skill-based agent routing, and manage ticket…