claude-vibe-squad: Skill for Claude Code

.agents/skills/security-ownership-map/SKILL.md

security-ownership-map is a skill for Claude Code, Codex from mtarcure/claude-vibe-squad. It costs 80 tokens per session (456 once invoked), scanned A, original, MIT.

A map showing which people or teams own each software component and who can make security decisions about it. It uses evidence such as code changes, deployments, and on-call records to identify patching, shutdown, and credential-change authority.

In plain words
What is it for?
Use it during security investigations, vulnerability response, or ownership reviews to assign contacts, confirm decision rights, and find components that cannot be acted on quickly.
Why use it?
Security fixes and incident response often stall when nobody knows who is responsible or authorized to act. The map highlights components with no clear owner, former owners, shared responsibility, or outside vendors.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is mtarcure/claude-vibe-squad's own configuration. It tells Claude Code and Codex how to work on claude-vibe-squad itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-vibe-squad configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mtarcure/claude-vibe-squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/.agents/skills/security-ownership-map/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mtarcure/claude-vibe-squad

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 security-ownership-map

README.md
[![agentmods](https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/security-ownership-map/github.svg)](https://agentmods.dev/skills/mtarcure/claude-vibe-squad/security-ownership-map)
Your own site
<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/security-ownership-map"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/security-ownership-map/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.

agentmods 80×15 button for security-ownership-map

Your own site · 80×15
<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/security-ownership-map"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/security-ownership-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00080 $0.00456
Opus 5 $0.00040 $0.00228
Sonnet 5 $0.00016 $0.00091
Haiku 4.5 $0.00008 $0.00046

Measured 10d ago against content hash fa25b100de66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

security-ownership-map 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 10d 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.

.agents/skills/security-ownership-map/SKILL.md · 27 lines

What it actually says

Security Ownership Map

Establish who owns each security-relevant component, so findings route to someone who can act and no surface is left unowned.

Steps

  1. Enumerate security-relevant components: authentication, authorization, secrets handling, data stores holding sensitive data, external integrations, deployment and CI, and the network edge.
  2. For each component, derive candidate owners from evidence — code ownership files, commit history concentration, deploy configuration, and on-call rotations — rather than from an org chart.
  3. Record for each component: owning team or person, escalation path, and the decision rights they actually hold (can they patch, can they take it offline, can they rotate its credentials).
  4. Flag every component with no owner, a departed owner, or an owner who lacks the rights to remediate. Unowned security surface is itself a finding.
  5. Flag shared-ownership components where responsibility is genuinely ambiguous; these are where findings stall longest.
  6. Map each finding class to the owner who can remediate it, distinguishing the owner of the code from the owner of the deployment where these differ.
  7. Note cross-boundary components — vendor-managed, contractor-built, or inherited — and record the contractual or practical limit on what can be changed.
  8. Date the map and name its evidence sources; ownership decays and an undated map silently misroutes.

Acceptance

  • Every security-relevant component has a named owner, escalation path, and stated decision rights, or is explicitly flagged unowned.
  • Ownership is derived from observable evidence, with the source cited per component.
  • Components whose owner cannot remediate are called out separately from unowned ones.
  • Finding classes are routed to the owner able to act on them.
  • The map carries a date and its evidence sources.
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. 10d ago First seen · 27 lines · 80 tokens per session scan A fa25b100de66

Subscribe to this mod's changes

security-ownership-map is a skill published in the GitHub repository mtarcure/claude-vibe-squad (142 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 456 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.