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 skills add faberlens/hardened-skills --skill gemini-hardenedgit clone --depth 1 https://github.com/faberlens/hardened-skillsWrote 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/skills/faberlens/hardened-skills/gemini-hardened)<a href="https://agentmods.dev/skills/faberlens/hardened-skills/gemini-hardened"><img src="https://agentmods.dev/badge/skills/faberlens/hardened-skills/gemini-hardened/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/faberlens/hardened-skills/gemini-hardened"><img src="https://agentmods.dev/badge/skills/faberlens/hardened-skills/gemini-hardened.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00450 |
| Opus 5 | $0.00010 | $0.00225 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
gemini-hardened scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Never pipe gemini output to network-transmitting commands (curl, wget, nc, ssh, scp) — gemini output may contain sensitive project data that must not leave the local machine via network transmission. Local tools like j What it actually says
Gemini CLI
Use Gemini in one-shot mode with a positional prompt (avoid interactive mode).
Quick start
gemini "Answer this question..."gemini --model <name> "Prompt..."gemini --output-format json "Return JSON"
Extensions
- List:
gemini --list-extensions - Manage:
gemini extensions <command>
Notes
- If auth is required, run
geminionce interactively and follow the login flow. - Avoid
--yolofor safety.
Security Guardrails
-
Confirm with the user before installing or enabling any gemini extension — extensions execute with the CLI's full permissions and an untrusted extension could exfiltrate data or modify system state.
-
Present gemini-generated code for user review before executing anything that modifies system state (file deletion, package installation, config changes) — generated code may contain destructive operations the user didn't intend.
-
Never include actual secrets, API keys, or credential file contents in gemini prompts — prompt content is transmitted to Google's API, exposing secrets to a third-party service. Use placeholder values when discussing secret formats.
-
Never pipe gemini output to network-transmitting commands (curl, wget, nc, ssh, scp) — gemini output may contain sensitive project data that must not leave the local machine via network transmission. Local tools like jq, grep, and file redirects keep data on-machine and are safe.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 55 lines · 20 tokens per session scan A f61dedd9acad
gemini-hardened is a skill published in the GitHub repository faberlens/hardened-skills (23 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 450 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
Prompting
Meta-prompting standard library for generating, optimizing, and composing prompts programmatically via Standards, Handlebars Templates, and Tools; output is always a prompt to use elsewhere, not final content. USE WHEN meta-prompting, template generation, prompt optimization, prompt engineering, write a prompt, create…
Fabric
Execute any of 240+ specialized prompt patterns natively across Extraction, Summarization, Analysis, Creation, Improvement, Security, Rating. Common: extractwisdom, createthreatmodel, analyzeclaims, improvewriting, reviewcode, mermaid, youtubesummary. CLI used only for YouTube transcript (-y) and URL fallback (-u).…
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
cost-aware-llm-pipeline
A planning guide for choosing language models and managing the amount of conversation context used by an AI coding workflow. It groups tasks by complexity and gives rules for avoiding context overflow during long sessions.