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 BagelHole/DevOps-Security-Agent-Skills --skill startup-it-troubleshootinggit clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-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/bagelhole/devops-security-agent-skills/startup-it-troubleshooting)<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/startup-it-troubleshooting"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/startup-it-troubleshooting/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/bagelhole/devops-security-agent-skills/startup-it-troubleshooting"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/startup-it-troubleshooting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 32 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 Tool Misuse · line 59 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 92 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 93 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 169 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 172 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 205 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 208 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 216 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 343 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 370 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Privilege Escalation · line 59 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 169 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 208 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 215 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 216 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 217 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 366 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 367 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 64 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 79 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.03528 |
| Opus 5 | $0.00010 | $0.01764 |
| Sonnet 5 | $0.00004 | $0.00706 |
| Haiku 4.5 | $0.00002 | $0.00353 |
Grade B, and why
startup-it-troubleshooting scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo dscacheutil -flushcache && sudo killall -HUP mDNSResponder Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash <(curl -s -S -L https://gam-shortn.appspot.com/gam-install) # install GAM How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Startup IT Troubleshooting
Runbooks for startups and small teams where engineers double as the IT department.
When to Use
You are the "accidental IT person." Nobody has IT in their title, but laptops freeze, Wi-Fi drops during investor demos, someone gets locked out of Google Workspace at midnight, and a new hire starts Monday with zero accounts. This skill gives you copy-paste commands to handle it all.
Priority triage: (1) Company-wide outages, (2) Executive/customer-facing blockers, (3) Team-wide degradations, (4) Individual workstation issues. Always ask: "How many people are affected?" and "Is revenue impacted?"
SSO / Identity Lockouts
Google Workspace via GAM
bash <(curl -s -S -L https://gam-shortn.appspot.com/gam-install) # install GAM
gam oauth create # authorize
gam update user [email protected] password "TempPass123!" changepassword on # reset password
gam update user [email protected] suspended off # unsuspend locked-out user
gam user [email protected] signout # force sign-out all sessions
gam user [email protected] update backupcodes # new MFA backup codes
gam user [email protected] turnoff2sv # disable 2SV (re-enable within 24h)
Okta API
OKTA="company.okta.com"; T="your-api-token"; UID="00u1abcdef"
curl -X POST -H "Authorization: SSWS $T" "https://$OKTA/api/v1/users/$UID/lifecycle/unlock"
curl -X POST -H "Authorization: SSWS $T" "https://$OKTA/api/v1/users/$UID/lifecycle/reset_password?sendEmail=true"
curl -X POST -H "Authorization: SSWS $T" "https://$OKTA/api/v1/users/$UID/lifecycle/reset_factors"
curl -X DELETE -H "Authorization: SSWS $T" "https://$OKTA/api/v1/users/$UID/sessions"
MFA recovery flow: Verify identity via video call, generate backup codes or reset factors, have user re-enroll immediately, confirm old device is deregistered, log the incident.
Network Troubleshooting
Wi-Fi Debugging
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 · 400 lines · 20 tokens per session scan B 1cb234d69e8c
startup-it-troubleshooting is a skill published in the GitHub repository BagelHole/DevOps-Security-Agent-Skills (1,071 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 3,528 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, 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
automated-remediation
An automated recovery procedure that selects a predefined runbook for a known service-failure pattern. A runbook is a documented sequence of operational recovery steps.
root-cause-analysis
An incident investigation tool that gathers metrics, logs, events, and change history to identify likely root causes. It connects related events on a timeline and produces a root-cause analysis report.
incident-response
An incident-response process that receives CloudWatch or Prometheus alerts, classifies their severity, consults runbooks, investigates possible causes, and prepares remediation for approval.
email-content-guide
Best practices for email content that avoids spam filters. Apply these rules when writing email copy, building templates, or debugging spam placement issues.
deslop
Remove AI-generated artifacts from code. Three-phase certainty-graded cleanup. Use after any AI implementation session or before PR creation.
b00t-maintenance
Access the b00t maintenance loop — check status, view cake token balance, confirm exercise reminders, and inspect the research queue. The 👍🏻/👎🏻 vote tokens feed the probabilistic cake lottery resolved at pre-commit review.