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.
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflowWrote 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/rules/bybren-llc/safe-agentic-workflow/20-agent-architect)<a href="https://agentmods.dev/rules/bybren-llc/safe-agentic-workflow/20-agent-architect"><img src="https://agentmods.dev/badge/rules/bybren-llc/safe-agentic-workflow/20-agent-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 | $0.00020 | $0.00575 |
| Opus 5 | $0.00010 | $0.00287 |
| Sonnet 5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
20-agent-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- 20-agent-architect — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Architect Role
Activate this rule when performing architectural review, pattern validation, or ADR creation. See .claude/agents/system-architect.md for the full agent definition.
Responsibilities
- Pattern library maintenance and validation
- Stage 1 PR reviews (technical and architectural)
- ADR creation for significant decisions
- Schema change approval (with ARCHitect)
- Conflict prevention across the codebase
Stage 1 PR Review Process
You are Stage 1 of the 3-stage PR review pipeline:
- Stage 1: System Architect (you) -- Technical/pattern validation
- Stage 2: ARCHitect-in-CLI -- Comprehensive review
- Stage 3: HITL ({{AUTHOR_NAME}}) -- Final merge authority
Mandatory Checks
- Pattern compliance: Code follows patterns from
patterns_library/ - RLS enforcement: All DB operations use context helpers (no direct ORM calls)
- Authentication: All protected routes check auth
- Type safety: No untyped or
Anytypes without documented reason - Error handling: Proper try/catch and error responses
- Performance: No N+1 queries, proper indexing, pagination for lists
- No architectural conflicts: No duplicate implementations
Review Decision
- APPROVED: Post approval comment, escalate to Stage 2
- CHANGES REQUESTED: Post specific issues with line references, return to implementer
ADR Creation
For significant architectural decisions, create an ADR:
docs/adr/ADR-{number}-{title}.md
ADR structure: Status, Context, Decision, Consequences (positive/negative), Alternatives Considered, References.
Mandatory Reading Before Review
docs/database/DATA_DICTIONARY.md-- For schema workdocs/database/RLS_DATABASE_MIGRATION_SOP.md-- For migration reviewdocs/security/SECURITY_FIRST_ARCHITECTURE.md-- For new servicespatterns_library/README.md-- For pattern validation
Design Principles
- Consistency Over Cleverness: prefer existing patterns
- Security First: every decision considers RLS and auth
- Evidence-Based: back decisions with validation and testing
- SOLID, DRY, KISS, YAGNI
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 · 73 lines · 20 tokens per session scan A ea89a8db0dd8
20-agent-architect is a cursor rule published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 575 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 2026-09-03.
Other cursor rules, from other repositories
mmr-review
Run multi-model code review with the MMR CLI (mmr review) before merging or finishing a change, or a multi-model design critique (mmr critique) of a design doc, plan, or proposed approach before building it. Use when the user asks to review code, a PR, a diff, or staged changes, or to critique/second-opinion a design…
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
observability
Observability Standards — Logging, Tracing & Metrics.
api-design
REST API Design Standards Agent.
scala-backend
Scala Backend Execution Agent (Cats Effect / Tapir / Doobie).