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 26zl/cybersec-toolkit --skill containing-active-breachgit clone --depth 1 https://github.com/26zl/cybersec-toolkitWrote 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/26zl/cybersec-toolkit/containing-active-breach)<a href="https://agentmods.dev/skills/26zl/cybersec-toolkit/containing-active-breach"><img src="https://agentmods.dev/badge/skills/26zl/cybersec-toolkit/containing-active-breach/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/26zl/cybersec-toolkit/containing-active-breach"><img src="https://agentmods.dev/badge/skills/26zl/cybersec-toolkit/containing-active-breach.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 | $0.00073 | $0.02248 |
| Opus 5 | $0.00036 | $0.01124 |
| Sonnet 5 | $0.00015 | $0.00450 |
| Haiku 4.5 | $0.00007 | $0.00225 |
Grade A, and why
containing-active-breach 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 5d 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
100% identical to containing-active-breach — 0 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Containing Active Breaches
When to Use
- A confirmed intrusion is in progress with an active adversary on the network
- Malware is spreading laterally across endpoints or servers
- A compromised account is being used for unauthorized access to systems
- Ransomware encryption has been detected and is actively propagating
- An attacker has established command-and-control communications from internal hosts
Do not use for post-incident cleanup when the adversary is no longer active; use eradication procedures instead.
Prerequisites
- Confirmed incident classification with P1 or P2 severity from triage
- EDR console access with host isolation capabilities (CrowdStrike Falcon, Microsoft Defender for Endpoint, SentinelOne)
- Network firewall and switch management access for segmentation
- Active Directory or identity provider administrative access for credential actions
- Pre-approved containment authority documented in the incident response plan
- Evidence preservation plan to avoid destroying forensic artifacts during containment
Workflow
Step 1: Assess Containment Scope
Before taking containment actions, map the full scope of compromise to avoid partial containment that alerts the adversary:
- Identify all confirmed compromised hosts via EDR telemetry and SIEM correlation
- Map lateral movement paths using authentication logs (Windows Event ID 4624 Type 3 and Type 10)
- Identify all compromised credentials (check for pass-the-hash, Kerberoasting, DCSync activity)
- Determine C2 channels (beacon intervals, domains, IPs, protocols)
- Assess whether the adversary has domain admin or equivalent privileges
Containment Scope Assessment:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Compromised Hosts: 5 (WKSTN-042, WKSTN-087, SRV-FILE01, SRV-DC02, WKSTN-103)
Compromised Accounts: 3 (jsmith, svc-backup, admin-tier0)
C2 Channels: HTTPS beacon to 185.220.x.x every 60s ± 15% jitter
Lateral Movement: PsExec via svc-backup, RDP via admin-tier0
Adversary Privilege: Domain Admin (admin-tier0 compromised)
Data at Risk: Finance share (\\SRV-FILE01\finance$) accessed
What ships with it
3 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.
- 5d ago First seen · 232 lines · 73 tokens per session scan A 3e8883aa791d
containing-active-breach is a skill published in the GitHub repository 26zl/cybersec-toolkit (51 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 2,248 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to containing-active-breach, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
containing-active-breach
Executes containment strategies to stop active adversary operations and prevent lateral movement during a confirmed security breach. Implements short-term and long-term containment using network segmentation, endpoint isolation, credential revocation, and access control modifications. Activates for requests involving…
containing-active-breach
Executes containment strategies to stop active adversary operations and prevent lateral movement during a confirmed security breach. Implements short-term and long-term containment using network segmentation, endpoint isolation, credential revocation, and access control modifications. Activates for requests involving…
detecting-azure-lateral-movement
Detect lateral movement in Azure AD/Entra ID environments using Microsoft Graph API audit logs, Azure Sentinel KQL hunting queries, and sign-in anomaly correlation to identify privilege escalation, token theft, and cross-tenant pivoting.
implementing-network-deception-with-honeypots
Deploy and manage network honeypots using OpenCanary, T-Pot, or Cowrie to detect unauthorized access, lateral movement, and attacker reconnaissance.
ad-exploitation
Active Directory exploitation skill — credential attacks, lateral movement, privilege escalation, and domain domination. Activate when the user wants to exploit an AD environment after enumeration, or mentions: Kerberoasting, AS-REP Roasting, pass-the-hash, pass-the-ticket, lateral movement, DCSync, Golden Ticket…
ad-postexploitation
Active Directory post-exploitation skill — covers everything after gaining initial access to a Windows domain environment. Activate when the user has valid domain credentials, a shell on a domain-joined machine, or escalated privileges and wants to: move laterally across the network, escalate to Domain Admin, harvest…