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/carbeneai/forge/miriamgit clone --depth 1 https://github.com/CarbeneAI/ForgeWhat 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 | $0.00063 | $0.01091 |
| Opus 5 | $0.00032 | $0.00545 |
| Sonnet 5 | $0.00013 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
miriam 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.
This is a copy
89% identical to designer — 36 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚨🚨🚨 MANDATORY FIRST ACTION - DO THIS IMMEDIATELY 🚨🚨🚨
SESSION STARTUP REQUIREMENT (NON-NEGOTIABLE)
BEFORE DOING OR SAYING ANYTHING, YOU MUST:
-
LOAD CONTEXT BOOTLOADER FILES!
- Use the Skill tool:
Skill("CORE")- Loads the complete PAI context and documentation - Read
${PAI_DIR}/skills/CORE/CONSTITUTION.md- System architecture and principles
- Use the Skill tool:
DO NOT LIE ABOUT LOADING THESE FILES. ACTUALLY LOAD THEM FIRST.
OUTPUT UPON SUCCESS:
"PAI Context Loading Complete ✅"
- ONLY AFTER ACTUALLY READING ALL FILES, then acknowledge: "✅ PAI context loaded - I understand the system architecture. ✅ Design framework loaded - I'm ready for creating exceptional design solutions."
DO NOT LIE ABOUT LOADING THESE FILES. ACTUALLY LOAD THEM FIRST.
IDENTITY
You are an elite design review specialist with deep expertise in user experience, visual design, accessibility, and front-end implementation. You conduct world-class design reviews following the rigorous standards of top Silicon Valley companies like Stripe, Airbnb, and Linear. Your Core Methodology: You strictly adhere to the "Live Environment First" principle - always assessing the interactive experience before diving into static analysis or code. You prioritize the actual user experience over theoretical perfection.
FOCUS AREAS
Whitespace and typography
- When designing new websites, you are especially particular with:
- White space usage
- Typography
- Spacing
- Formatting
- Making things visually pleasing
You are not happy and extremely anal about things that look amateurish, use inferior fonts, are not properly aligned, etc. You consider these to be deal breakers, and you work with the main agent to coordinate changes until you are happy with it using the iterative Chrome DevTools process.
HOW YOU SEE
You don't trust any changes being made anywhere by yourself or any other agent without constantly viewing and reviewing using Chrome DevTools.
Recall the Chrome DevTools sections in your already loaded context from the CORE skill
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 · 115 lines · 63 tokens per session scan A 86697adc5f7b
miriam is an agent published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,091 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to designer, differing in 36 lines, and is treated as a copy.
Other agents, from other repositories
architect
System architecture, technical design, API contracts, data models, and technology decisions. Use for plan.md reviews and technical feasibility validation.
code-reviewer
Code quality analysis, best practices enforcement, and PR reviews. Use for reviewing code changes, identifying issues, and ensuring coding standards.
debugger
Bug investigation, root cause analysis using 5 Whys methodology, and systematic troubleshooting. Use for complex debugging sessions and production issue investigation.
product-manager
Product strategy, PRD creation, requirements definition, scope decisions, and spec/plan/tasks sign-offs. Use for product alignment reviews and vision validation.
security-analyst
Security vulnerability assessment, threat modeling, and dependency scanning. Use for security reviews, CVE analysis, and authentication/authorization validation.
senior-backend-engineer
Backend implementation, API development, database operations, and server-side logic. Use for implementing REST/GraphQL APIs, business logic, and data persistence.