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/jeonje/claude-plugins/architectgit clone --depth 1 https://github.com/JeonJe/claude-pluginsWhat 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 | $0.00000 | $0.00211 |
| Opus 5 | $0.00000 | $0.00105 |
| Sonnet 5 | $0.00000 | $0.00042 |
| Haiku 4.5 | $0.00000 | $0.00021 |
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 2d 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
Architect — design alignment
Read at: code mode — contract/architecture reviewer lane dispatch · Produces: contract-alignment findings (Verdict/Findings/Evidence/Risk) · Shared knowledge.
Inspects: API contract, cross-project, arch adherence
Review steps
- API contract: design API ↔ impl
- endpoint URL/method match
- req/res DTO field map
- error code/response shape
- Architecture adherence: layer separation, dep direction, design pattern
- Design-contract verification: extraction assigns
DC-Nto each testable API/data/constraint contract; verify every DC - Cross-project: FE↔BE consistency (when applicable) — see
../checklists/cross-project.md
Output
[ARCH] DC-1: PASS — {evidence}
[ARCH] DC-2: FAIL — {mismatch}
[ARCH] CROSS — {consistency issue or "none"}
Single-project change → omit CROSS.
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.
- 2d ago First seen · 26 lines · 0 tokens per session scan A 5f587dad34c6
architect is an agent published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 211 tokens. 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
docs
Generate documentation from code. Creates README files, API references, and inline documentation based on code analysis.
code-reviewer
Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.
interactive-element-creator
Implements interactive JavaScript components for presentations (tabs, accordions, charts).
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.
quant-ml-validator
Validates data integrity, feature engineering, and model training to prevent look-ahead bias and survivorship errors.
code-researcher
Researches a codebase's architecture, data flows, and component relationships and returns synthesized findings with file:line citations. Use proactively for architectural questions, multi-file dependency tracing, impact analysis before a refactoring, and onboarding to unfamiliar code — any wide investigation that…