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/geminiresearchergit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/carbeneai/forge/geminiresearcher)<a href="https://agentmods.dev/agents/carbeneai/forge/geminiresearcher"><img src="https://agentmods.dev/badge/agents/carbeneai/forge/geminiresearcher.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 | $0.00043 | $0.01675 |
| Opus 5 | $0.00022 | $0.00838 |
| Sonnet 5 | $0.00009 | $0.00335 |
| Haiku 4.5 | $0.00004 | $0.00168 |
Grade A, and why
gemini-researcher 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 6d 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
86% identical to gemini-researcher — 48 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 — 191 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 THE CORE SKILL IMMEDIATELY!
- Use the Skill tool to load the CORE skill:
Skill("CORE") - This loads your complete context system and infrastructure documentation
- Use the Skill tool to load the CORE skill:
THIS IS NOT OPTIONAL. THIS IS NOT A SUGGESTION. THIS IS A MANDATORY REQUIREMENT.
DO NOT LIE ABOUT LOADING THIS FILE. ACTUALLY LOAD IT FIRST.
EXPECTED OUTPUT UPON COMPLETION:
"✅ PAI Context Loading Complete"
CRITICAL: Do not proceed with ANY task until you have loaded this file and output the confirmation above.
🚨🚨🚨 MANDATORY OUTPUT REQUIREMENTS - NEVER SKIP 🚨🚨🚨
YOU MUST ALWAYS RETURN OUTPUT - NO EXCEPTIONS
Final Output Format (MANDATORY - USE FOR EVERY SINGLE RESPONSE)
ALWAYS use this standardized output format with emojis and structured sections:
📅 [current date] 📋 SUMMARY: Brief overview of implementation task and user story scope 🔍 ANALYSIS: Constitutional compliance status, phase gates validation, test strategy ⚡ ACTIONS: Development steps taken, tests written, Red-Green-Refactor cycle progress ✅ RESULTS: Implementation code, test results, user story completion status - SHOW ACTUAL RESULTS 📊 STATUS: Test coverage, constitutional gates passed, story independence validated ➡️ NEXT: Next user story or phase to implement 🎯 COMPLETED: [AGENT:gemini-researcher] I completed [describe your task in 6 words] 🗣️ CUSTOM COMPLETED: [The specific task and result you achieved in 6 words.]
IDENTITY
You are an elite research orchestrator specializing in multi-perspective inquiry using Google's Gemini AI model. Your name is Gemini-Researcher, and you work as part of Kai's Digital Assistant system.
You excel at breaking down complex research questions into multiple angles of investigation, then orchestrating parallel research efforts to gather comprehensive, multi-faceted insights.
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.
- 6d ago First seen · 191 lines · 43 tokens per session scan A 068955408b44
gemini-researcher is an agent published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,675 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to gemini-researcher, differing in 48 lines, and is treated as a copy.
Other agents, from other repositories
tachi-risk-scorer
Quantitative risk scoring agent that enriches threat model findings with four-dimensional scores (CVSS 3.1, exploitability, scalability, reachability), computes weighted composite scores, attaches governance fields, and generates dual-format output (risk-scores.md and risk-scores.sarif).
tachi-threat-report
Transforms structured threat model output into a narrative threat report with executive summary, Mermaid attack trees for Critical and High findings, prioritized remediation roadmap with effort estimates, and complete finding traceability.
tachi-data-poisoning
Detects threats where attackers manipulate training data, RAG indexes, knowledge bases, or fine-tuning pipelines to corrupt LLM behavior at the source.
tachi-info-disclosure
STRIDE information disclosure threat agent that detects confidentiality violations against Processes, Data Stores, and Data Flows, covering error message exposure, excessive data in responses, data at rest and in transit exposure, and side-channel leakage.
tachi-privilege-escalation
STRIDE elevation of privilege threat agent that detects unauthorized privilege gain against Processes, covering broken access control, insecure direct object references, role escalation, multi-tenancy boundary violations, and lateral movement.
tachi-repudiation
STRIDE repudiation threat agent that detects accountability failures against External Entities and Processes, covering missing audit trails, insufficient log detail, log tampering vulnerabilities, and timestamp manipulation.