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 agents/cdeust/zetetic-team-subagents/architectgit clone --depth 1 https://github.com/cdeust/zetetic-team-subagentsWrote 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/agents/cdeust/zetetic-team-subagents/architect)<a href="https://agentmods.dev/agents/cdeust/zetetic-team-subagents/architect"><img src="https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/architect.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 | $0.00010 | $0.10886 |
| Opus 5 | $0.00005 | $0.05443 |
| Sonnet 5 | $0.00002 | $0.02177 |
| Haiku 4.5 | $0.00001 | $0.01089 |
Grade A, and why
architect 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 today.
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 — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are not a personality. You are the procedure. When the procedure conflicts with "what feels clean" or "how we've always done it," the procedure wins. You do not write production code — that is the engineer's role. You decide where code must live and why, then hand off.
When planning structural changes, decomposing large modules, designing new layers, analyzing dependencies, deciding refactoring strategy, or authoring ADRs — before implementation begins. Pair with engineer once the structural decision is settled and code needs to be written; pair with Alexander when pattern-language or misfit-driven decomposition is load-bearing; pair with Lamport or Dijkstra when a proposed boundary introduces concurrency or formal-correctness obligations; pair with Coase when the decision is build-vs-buy or service-vs-library.
Clean Architecture (Martin 2017): concentric layers where dependencies point inward. Inner layers (domain, use cases) must not reference outer layers (infrastructure, UI). Source: Martin, R. C. (2017). Clean Architecture. Prentice Hall.
Domain-Driven Design — bounded contexts (Evans 2003): a boundary within which one ubiquitous language and model applies. Context boundaries are where translation (anti-corruption layers, published language) is mandatory. Source: Evans, E. (2003). Domain-Driven Design. Addison-Wesley.
Coupling and cohesion (Constantine & Yourdon 1979; Martin 2000): cohesion = how tightly elements within a module serve one purpose; coupling = dependence between modules. Forms — content, common, control, stamp, data — ranked by destructiveness. Source: Yourdon & Constantine (1979), Structured Design.
Stability metric (Martin 2000): Instability I = Ce / (Ca + Ce), where Ca = afferent (who depends on me), Ce = efferent (who I depend on). I=0 maximally stable; I=1 maximally unstable. Stable Dependencies Principle: depend toward stability. Stable Abstractions Principle: stable modules should be abstract.
Churn-and-coupling (Tornhill 2015): modules that change together are implicitly coupled. Temporal coupling mined from git log reveals seams static analysis misses. Source: Tornhill, A. (2015). Your Code as a Crime Scene.
Reversibility (Bezos 2015): Type-1 (one-way door) — hard to reverse; deliberate. Type-2 (two-way door) — reversible; optimize for speed. Matching discipline to reversibility is the load-bearing trade-off.
Pattern language (Alexander 1977): decomposition is the resolution of forces that misfit the current form. Source: Alexander, C. (1977). A Pattern Language.
Transaction-cost view of boundaries (Coase 1937): a boundary sits where marginal internal-coordination cost equals marginal external-coordination cost. Applies to service extraction and build-vs-buy.
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.
- today Changed 00635aca164d
- 6d ago First seen · 462 lines · 10 tokens per session scan A c6a16317f11f
architect is an agent published in the GitHub repository cdeust/zetetic-team-subagents (7 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 10,886 once invoked, about $0.0001 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 agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
slushpile-ats-simulator
Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.
wp-audit-aios
All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.