Opsec Planning logo

Opsec Planning

Organization
zero-lab-ai
opsec-planning

Builds red-team OPSEC plans that connect an authorized objective to observable artifacts, detection risk, countermeasures, abort conditions, cleanup, and post-operation review. Use before a significant action or attack chain when stealth matters, when choosing between noisy and quiet approaches, or when an operator needs an auditable go/no-go decision.

Overview

Publisherzero-lab-ai
Repositoryskills
Skill nameopsec-planning
Stars
232
Forks
14
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zero-lab-ai on GitHub. Read the source before you install it.

Installation

Install the Opsec Planning AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zero-lab-ai/skills/tree/main/plugins/recon-operations/skills/opsec-planning
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zero-lab-ai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/recon-operations/skills/opsec-planning .claude/skills/opsec-planning
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Opsec Planning in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Opsec Planning on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Opsec Planning is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OPSEC planning

OPSEC is deliberate risk selection. The goal is not zero telemetry; every meaningful action leaves evidence somewhere. The output is a plan that states what the operation protects, who can observe it, which artifacts each action creates, why the risk is worth taking, and when the operator stops.

This skill operates only inside written authorization. It helps choose among authorized actions and never expands scope or grants permission to execute.

When to Use

  • Use OPSEC Planning for authorized security work.
  • Use only within explicit authorization and the stated rules of engagement.

When NOT to Use

  • Do not treat this skill as permission to access, test, or change a target.
  • Do not convert missing evidence into a clean result or a stronger claim.

Build the plan

  1. State the objective and posture. Define the smallest proof that satisfies the engagement objective. Choose maximum stealth, balanced, or speed priority.
  2. Identify critical information. Record what would expose the operation: infrastructure, identities, tooling, credentials, timing, and target pattern.
  3. Model the observers. Name the people and controls able to see the work and the telemetry available to them. Unknown visibility increases uncertainty; it does not count as absence of monitoring.
  4. Reduce the chain. Remove actions that do not directly advance the stated objective. Being in scope makes an action permissible, not necessary.
  5. Account for four surfaces. For every remaining action, describe disk, memory, log, and network artifacts. If a surface has no expected artifact, say why. Never leave it blank.
  6. Score before mitigation. Estimate detection probability from 0.0 to 1.0, detection impact from 1 to 10, and success value from 1 to 10. Compute risk = probability × impact and record the evidence behind the estimates.
  7. Choose and link countermeasures. Each countermeasure references the exposure it changes. Explicitly accept any remaining exposure; silence is not acceptance. Recalculate residual probability and risk.
  8. Set stop and recovery conditions. Give each action a concrete abort condition. Cover every artifact with removal, reversion, expiration verification, authorized retention, or documentation as unremovable.
  9. Plan the detection review. Name the telemetry or coordination evidence that will confirm what fired and what did not.

Decision thresholds

Initial or residual riskSuccess valueConsistent decision
< 3> 5execute
3 to < 5> 7execute with caution
5 to 8anymitigate first
> 8anyabort or request authorization

The source method leaves low-value gaps between its explicit thresholds. In those gaps, abort or request authorization rather than inventing permission. At the shared boundary of 5, use the safer mitigate-first decision.

Judgment calls

  • Probability needs evidence. Base it on observed controls, telemetry, baselines, and prior validation. A precise decimal with no evidence is still a guess.
  • A linked countermeasure may still be weak. A complete record shows that every exposure was addressed or accepted; it cannot prove the proposed change reduces detection.
  • Normal-looking is environment-specific. Native tooling and business-hour activity can be more visible when the baseline says they are unusual.
  • Residual risk is a new claim. Explain what changed between the initial and residual probability. Do not lower the number merely because a mitigation was written down.
  • Authorization remains external. A complete record validates the document, not the action. Required human approval still governs execution.

Rationalizations to reject

ThoughtReality
"It is in scope, so we should test it."Scope permits an action. The objective decides whether it belongs in this chain.
"This native command will blend in."Native is not invisible. Decide from the target's baseline and monitored channels.
"We will clean it up afterward."Logs and network records may be immutable. Name them and document them instead of promising deletion.
"The risk score is low enough."A score without evidence for probability and impact is decorative arithmetic.
"The countermeasure handles it."State which exposure changes and why the residual probability is lower.
"We can decide the stop condition live."Fatigue and proximity to the objective bias the operator toward continuing. Set the stop before execution.
"A complete record means go."It means the plan is internally consistent. Authorization and operator judgment still control execution.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Opsec Planning AI skill do?

Builds red-team OPSEC plans that connect an authorized objective to observable artifacts, detection risk, countermeasures, abort conditions, cleanup, and post-operation review. Use before a significant action or attack chain when stealth matters, when choosing between noisy and quiet approaches, or when an operator needs an auditable go/no-go decision.

Why use Opsec Planning on TypingMind?

Because you install it once and use it with any model. Opsec Planning is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Opsec Planning in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zero-lab-ai/skills/tree/main/plugins/recon-operations/skills/opsec-planning. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Opsec Planning?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Opsec Planning?

As many as you like. As long as a model supports skills, you can use Opsec Planning with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Opsec Planning AI skill free?

Yes. It is published on GitHub by zero-lab-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇