Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gemini-cli-extensions/srenpx agentmods add skills/gemini-cli-extensions/sre/safe-sre-investigatorWrote 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/sre/safe-sre-investigator)<a href="https://agentmods.dev/skills/gemini-cli-extensions/sre/safe-sre-investigator"><img src="https://agentmods.dev/badge/skills/gemini-cli-extensions/sre/safe-sre-investigator/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/gemini-cli-extensions/sre/safe-sre-investigator"><img src="https://agentmods.dev/badge/skills/gemini-cli-extensions/sre/safe-sre-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 50 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Rogue Agent · line 49 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00056 | $0.00879 |
| Opus 5 | $0.00028 | $0.00439 |
| Sonnet 5 | $0.00011 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
safe-sre-investigator 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 13d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe SRE Investigator
This skill helps set up and use dedicated read-only Service Accounts for investigating GCP and Kubernetes resources.
It provides wrapper scripts safe_gcloud and safe_kubectl to ensure commands are run with these limited-privilege accounts.
When suggesting commands, it includes a risk assessment.
Core Tasks
- Setup GCP: Initialize the GCP service account and
safe_gcloudscript. - Setup Kubernetes: Initialize the Kubernetes service account and
safe_kubectlscript for a specific cluster. - Suggest Commands: Provide
gcloudorkubectlcommands with risk assessments.
1. Setup GCP (safe_gcloud)
When first using this skill for a project, or if the user asks for setup, guide them through the one-time setup process for GCP access.
Action: Ask the user for the Project ID.
Script: Run the setup script:
bash ./scripts/setup_safe_sre_investigator.sh PROJECT_ID
- This script is idempotent.
- It creates
~/bin/safe_gcloud. - The user might need to re-source their shell profile.
- IAM roles are in
references/iam_roles.md.
2. Setup Kubernetes (safe_kubectl)
This setup must be run for EACH Kubernetes cluster you want to investigate.
Action: Ask the user for the Cluster Name and Cluster Location (Zone or Region).
Script: Run the setup script:
bash ./scripts/setup_safe_kubectl.sh CLUSTER_NAME CLUSTER_LOCATION
- This script needs to be run with user credentials that have permissions to create ServiceAccounts and ClusterRoleBindings in the target cluster.
- It creates a read-only ServiceAccount in the cluster and generates a dedicated kubeconfig in
~/.kube/safe-investigator-configs/. - It also creates
~/bin/safe_kubectl. - The K8s roles are in
references/k8s_readonly_role.yaml.
3. Suggesting Commands
When the user asks for a command:
- GCP: Use
safe_gcloud PROJECT_ID <gcloud commands>. - Kubernetes: Use
safe_kubectl CLUSTER_NAME -- <kubectl commands>. - Risk Assessment: ALWAYS include a risk assessment block. See
references/risk_assessment.md. - Write Operations: For commands requiring write access, provide the standard
gcloudorkubectlcommand and warn the user to run it with their own credentials, noting the risks.
What ships with it
8 files 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.
- 13d ago First seen · 88 lines · 56 tokens per session scan A dce333683767
safe-sre-investigator is a skill published in the GitHub repository gemini-cli-extensions/sre (83 stars, last pushed 10d ago), licensed Apache-2.0. It adds 56 tokens to every session and 879 once invoked, about $0.0003 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
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger keywords - openshell…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
azure-cloud-migrate
Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud…
atmos-helmfile
Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, varfile generation, EKS integration, source management.