vciso

vciso is a skill for Claude Code, Codex from UnitOneAI/SecuritySkills. It costs 71 tokens per session (4,805 once invoked), scanned A, original, MIT.

A virtual chief information security officer (CISO) guide for organizations without a full-time security leader. It structures security assessments, compliance preparation, risk management, and board reporting.

In plain words
What is it for?
It helps assess security maturity, prepare for SOC 2 audits, review risk after incidents, oversee AI adoption, and prepare reports for boards or investors.
Why use it?
It turns scattered security work into an organized program with clear assessments, remediation plans, and business-focused reports.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/unitoneai/securityskills/vciso
Any agent
npx skills add UnitOneAI/SecuritySkills --skill vciso
Clone the repo
git clone --depth 1 https://github.com/UnitOneAI/SecuritySkills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vciso

README.md
[![agentmods](https://agentmods.dev/badge/skills/unitoneai/securityskills/vciso.svg)](https://agentmods.dev/skills/unitoneai/securityskills/vciso)
Your own site
<a href="https://agentmods.dev/skills/unitoneai/securityskills/vciso"><img src="https://agentmods.dev/badge/skills/unitoneai/securityskills/vciso.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00071 $0.04805
Opus 5 $0.00036 $0.02403
Sonnet 5 $0.00014 $0.00961
Haiku 4.5 $0.00007 $0.00481

Measured 5d ago against content hash 77bae74b851f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vciso 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.

roles/vciso/SKILL.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Virtual CISO Role Bundle

A fractional CISO engagement guide that sequences security skills into coherent programs. This bundle replaces ad-hoc security work with structured engagement patterns that produce measurable outcomes.


When to Use

Invoke this role bundle when any of the following conditions are true:

  • No dedicated CISO. The organization lacks a full-time security leader and needs someone to own the security program, even part-time.
  • Security program assessment. Leadership wants to understand the current maturity of security controls, policies, and operations against a recognized framework.
  • Preparing for SOC 2 audit. The company is 60-180 days from a SOC 2 Type I or Type II audit and needs structured gap analysis and remediation planning.
  • Board wants a security posture report. The board or investors have requested a summary of security risk in business terms, not a vulnerability dump.
  • Post-incident program review. A significant incident has occurred and the organization needs to assess whether the broader security program failed, not just the individual control.
  • AI/LLM adoption oversight. Engineering is shipping LLM-powered features and nobody has evaluated the threat surface those introduce.

If the ask is a single tactical task (e.g., "scan this repo for secrets"), use the individual skill directly. This bundle is for program-level work.


Engagement Types

Each engagement type defines a skill sequence. Run the skills in order — each one produces outputs consumed by the next.

1. New Engagement / Baseline Assessment

Trigger: First 30 days with a new client, or annual reassessment.

Skill sequence:

nist-csf-assessment → soc2-gap → iam-review → cve-triage → threat-modeling
Step Skill Purpose
1 nist-csf-assessment Establish current maturity across all six CSF functions (Govern, Identify, Protect, Detect, Respond, Recover). This is the foundation — everything else references it.
2 soc2-gap Map CSF findings to SOC 2 Trust Services Criteria. Even if SOC 2 is not an immediate goal, this surfaces the controls gap in a format auditors and customers understand.
3 iam-review Evaluate identity and access management. IAM is the single highest-leverage control domain — misconfigured IAM is the root cause of the majority of breaches.
4 cve-triage Assess the current vulnerability landscape across infrastructure and applications. Produces the quantitative risk data the board cares about.
5 threat-modeling Model the top 3-5 threat scenarios specific to this organization's business, architecture, and data. Converts raw findings into a risk narrative.

Read the full file on GitHub · 397 lines

Changes

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.

  1. 5d ago First seen · 397 lines · 71 tokens per session scan A 77bae74b851f

Subscribe to this mod's changes

vciso is a skill published in the GitHub repository UnitOneAI/SecuritySkills (58 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 4,805 once invoked, about $0.0004 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.