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 skills/gemini-cli-extensions/security/pocnpx skills add gemini-cli-extensions/security --skill pocgit clone --depth 1 https://github.com/gemini-cli-extensions/securityWhat 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 | $0.00025 | $0.00423 |
| Opus 5 | $0.00013 | $0.00211 |
| Sonnet 5 | $0.00005 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
poc 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.
What it actually says
You are a security expert. Your task is to generate a Proof-of-Concept (PoC) for a vulnerability. You MUST call the poc_context tool BEFORE attempting to write any PoC code. The poc_context tool will execute the setup and return the exact context and directory paths you need to actually generate the PoC script. If multiple vulnerabilities are present, use the ask_user tool to ask which one to test.
Your Steps:
-
Call
poc_contextTool:- Extract the
problemStatement,vulnerabilityType, and exactsourceCodeLocationfrom the user context. If the problemStatement does not contain the exact file path, you MUST use your search tools to find the vulnerable file in the codebase BEFORE calling the tool. - Call the
poc_contexttool with these arguments. - The tool will return JSON containing coordinates:
language,pocDir,pocFileName, andextraInstructions. Keep these coordinates for the following steps.
- Extract the
-
Use Dependency Manager Guidelines:
- Use the
dependency-managerskill to install dependencies for the PoC.
- Use the
-
Generate PoC:
- The PoC directory
pocDirhas been created for your scratchwork. - Generate your standalone script named exactly as
pocFileNameunder the returnedpocDir. - Pay attention to any
extraInstructionsreturned bypoc_context.
- The PoC directory
-
Run PoC:
- Use the
run_poctool with the absolute file path to the generated PoC file to execute the code. - Analyze the output to verify if the vulnerability is reproducible.
- If reproducible, use the
ask_usertool to ask if the user wants to fix it.
- Use the
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 · 27 lines · 25 tokens per session scan A c193f694944a
poc is a skill published in the GitHub repository gemini-cli-extensions/security (791 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 423 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 2026-08-30.
Other skills, from other repositories
ticket-manager
Expertise in managing Linear tickets locally using Markdown files. Use when you need to create, update, search, or break down features into atomic implementation tickets.
plan-reviewer
Expertise in reviewing implementation plans for architectural soundness, specificity, and safety. Use before implementation to prevent "vague plans" and "messy code.".
prd-drafter
Pickle Rick's PRD Engine. Use when you need to define the requirements, scope, and goals for a new feature or project before coding to avoid "Jerry-work.".
code-researcher
Expertise in conducting technical research on codebase tasks and documentation. Use when you need to understand existing implementations, trace data flows, or map codebase patterns.
research-reviewer
Expertise in reviewing technical research for objectivity, evidence, and completeness. Use to ensure the "Documentarian" standard is met.
implementation-planner
Expertise in creating detailed, atomic, and safe implementation plans. Use when you need to transform requirements into a step-by-step technical execution strategy.