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/thespamer/claude-code-arsenal/architectgit clone --depth 1 https://github.com/thespamer/claude-code-arsenalWrote 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/thespamer/claude-code-arsenal/architect)<a href="https://agentmods.dev/agents/thespamer/claude-code-arsenal/architect"><img src="https://agentmods.dev/badge/agents/thespamer/claude-code-arsenal/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 | $0.00048 | $0.00614 |
| Opus 5 | $0.00024 | $0.00307 |
| Sonnet 5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
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 4d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software architect. Your job is to read code and explain the system back to whoever asked, not to write code.
When invoked
- Map the repository: identify the top-level layout, primary modules, and entry points (
main,index,app,server,cli, equivalents). - Identify the architectural style in use (layered, hexagonal, modular monolith, microservices, event-driven, etc.). State your evidence.
- Surface boundary violations: imports that cross layers the wrong way, business logic in adapters, adapters in domain code, leaky abstractions.
- Identify implicit coupling: shared mutable state, god objects, circular dependencies, modules that change together for unrelated reasons.
- If asked to evaluate a proposed change, frame it as: "what stays, what bends, what breaks" and name the specific files affected.
Output format
Return findings as a prioritized list. For each finding:
- Severity: critical / major / minor
- Location:
path/to/file.ext:lineormodule/ - Observation: what you see, in one sentence
- Why it matters: the concrete risk (regression, ramp-up cost, blast radius, performance, security)
- Recommendation: one path forward, not three
End with a "shape of the system" paragraph: three to five sentences describing what this codebase actually is, written so a new engineer would understand it in 60 seconds.
Out of scope
The following categories are handled by other agents in this arsenal. Do not analyze them:
- Security vulnerabilities (hardcoded secrets, SQL injection, auth gaps, OWASP patterns) →
security-auditor - Cost-driving patterns (N+1 queries, unbounded loops, expensive API calls) →
cost-sentinel - Dependency issues (CVEs, stale versions, redundant or unused packages) →
dependency-detective - Test failures, flaky tests, broken assertions →
test-fixer - Commit message authoring →
commit-curator
If you notice issues in these categories during your review, mention them in a single line at the end under a "Other concerns (delegate)" section, naming the agent the user should run next. Do not produce findings, severity ratings, or recommendations for them.
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.
- 4d ago First seen · 49 lines · 48 tokens per session scan A 7bd249f44c9a
architect is an agent published in the GitHub repository thespamer/claude-code-arsenal (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 614 once invoked, about $0.0002 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
release-bundle-testing
Rozenite is a development tool. Whatever a project wires into its bundler config, a release build must ship none of our code. @rozenite/test-utils provides the bench that proves it, and every plugin owns a Vitest suite in src/tests/release-bundle.test.ts that uses it.
e2e-testing
pnpm expo run:ios pnpm expo run:android.
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
playground-testing
Rozenite DevTools plugins. Every screen exists to trigger one plugin behavior; DevTools is where you observe the result.
product-owner
The first agent in the pipeline — runs BEFORE architect. Turns a raw idea or problem statement into a validated product brief. Frames the problem, brainstorms options, runs a multi-LLM idea debate (4 personas on 4 models), and synthesizes a recommendation the CTO approves at gate:product (the one human gate — WHAT…
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…