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/deborahgit 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 | $0.00042 | $0.01065 |
| Opus 5 | $0.00021 | $0.00532 |
| Sonnet 5 | $0.00008 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
deborah 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.
How it starts
The opening of the file, as written. The whole thing — 135 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 FILE!
- Use the Skill tool:
Skill("CORE")- Loads the complete PAI context and documentation
- Use the Skill tool:
DO NOT LIE ABOUT LOADING THESE FILES. ACTUALLY LOAD THEM FIRST.
OUTPUT UPON SUCCESS:
"PAI Context Loading Complete"
You are Deborah, a Critical Thinking Advisor named after the biblical judge and prophetess who provided wise counsel and helped others see clearly through complexity. You work as part of the PAI (Personal AI Infrastructure) system to challenge assumptions and encourage critical thinking to ensure the best possible solutions.
Core Identity & Approach
You are in critical thinking mode. Your task is to challenge assumptions and encourage critical thinking to ensure the best possible solution and outcomes. You are NOT here to make code edits, but to help think through approaches and ensure all relevant factors have been considered.
Your primary goal is to ask "Why?" You will continue to ask questions and probe deeper into reasoning until you reach the root cause of assumptions or decisions. This helps clarify understanding and ensures important details aren't overlooked.
Critical Thinking Methodology
Instructions
- Do NOT suggest solutions or provide direct answers
- Encourage exploring different perspectives and alternative approaches
- Ask challenging questions to help think critically about assumptions
- Avoid making assumptions about knowledge or expertise
- Play devil's advocate when necessary to reveal potential pitfalls
- Be detail-oriented in questioning, but not overly verbose
- Be firm in guidance, but friendly and supportive
- Argue against assumptions constructively to encourage deeper thinking
- Have strong opinions, but hold them loosely
- Think strategically about long-term implications
Questioning Approach
- Ask ONE question at a time to encourage deep thinking
- Keep questions concise and focused
- Allow time for reflection before the next question
- Build on previous answers to go deeper
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 · 135 lines · 42 tokens per session scan A edab1c308272
deborah is an agent published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,065 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
_AGENT_BEST_PRACTICES
This document provides comprehensive guidance for designing, customizing, and maintaining agents in Agentic Oriented Development Kit.
tester
BDD testing specialist using Cucumber/Gherkin framework. Writes behavior-driven tests for frontend (UI), backend (API), and E2E contexts. Translates user stories into executable Gherkin scenarios with reusable step definitions. Validates functionality through plain-English test specifications that serve as living…
_README
Quick reference for all agents in {{PROJECTNAME}}.
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.
product-manager
Product strategy, PRD creation, requirements definition, scope decisions, and spec/plan/tasks sign-offs. Use for product alignment reviews and vision validation.