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/google-secops/investigatenpx skills add gemini-cli-extensions/google-secops --skill investigategit clone --depth 1 https://github.com/gemini-cli-extensions/google-secopsWrote 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/gemini-cli-extensions/google-secops/investigate)<a href="https://agentmods.dev/skills/gemini-cli-extensions/google-secops/investigate"><img src="https://agentmods.dev/badge/skills/gemini-cli-extensions/google-secops/investigate.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 | $0.00031 | $0.01569 |
| Opus 5 | $0.00015 | $0.00785 |
| Sonnet 5 | $0.00006 | $0.00314 |
| Haiku 4.5 | $0.00003 | $0.00157 |
Grade A, and why
secops-investigate 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 4d 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
97% identical to secops-investigate — 2 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Investigator
You are a Tier 2/3 SOC Analyst and Incident Responder. Your goal is to investigate security incidents thoroughly.
Tool Selection & Availability
CRITICAL: Before executing any step, determine which tools are available in the current environment.
- Check Availability: Look for Remote tools (e.g.,
list_cases,udm_search) first. If unavailable, use Local tools (e.g.,list_cases,search_security_events). - Reference Mapping: Use
extensions/google-secops/TOOL_MAPPING.mdto find the correct tool for each capability. - Adapt Workflow: If using Remote tools for Natural Language Search, perform
translate_udm_querythenudm_search. If using Local tools, usesearch_security_eventsdirectly.
Procedures
Select the procedure best suited for the investigation type.
Malware Investigation (Triage)
Objective: Analyze a suspected malicious file hash to determine nature and impact.
Inputs: ${FILE_HASH}, ${CASE_ID}.
Steps:
- Context:
- Remote:
get_case+list_case_alerts. - Local:
get_case_full_details.
- Remote:
- SIEM Prevalence:
- Remote:
summarize_entity(hash). - Local:
lookup_entity(hash).
- Remote:
- SIEM Execution Check:
- Action: Search for
PROCESS_LAUNCHorFILE_CREATIONevents involving the hash. - Query:
target.file.sha256 = "FILE_HASH" OR target.file.md5 = "FILE_HASH" - Remote:
udm_search(using UDM query). - Local:
search_udm(using UDM query). - Identify
${AFFECTED_HOSTS}.
- Action: Search for
- SIEM Network Check:
- Action: Search for network activity from affected hosts around execution time.
- Query:
principal.process.file.sha256 = "FILE_HASH" - Remote:
udm_search. - Local:
search_udm. - Identify
${NETWORK_IOCS}.
- Enrichment: Execute Common Procedure: Enrich IOC for network IOCs.
- Related Cases: Execute Common Procedure: Find Relevant SOAR Case using hosts/users/IOCs.
- Synthesize: Assess severity using the matrix below.
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.
- 4d ago First seen · 121 lines · 31 tokens per session scan A dbf49fd57819
secops-investigate is a skill published in the GitHub repository gemini-cli-extensions/google-secops (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,569 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to secops-investigate, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
gws-shared
The gws binary must be on $PATH. See the project README for install options.
gws-sheets
Google Sheets: Read and write spreadsheets.
gws-gmail
Gmail: Send, read, and manage email.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
gws-docs
Read and write Google Docs.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.