cso

cso is a skill for Claude Code, Codex from timurgaleev/vibestack. It costs 104 tokens per session (12,805 once invoked), scanned C, a copy of cso, MIT.

A security-audit workflow led from an infrastructure perspective. It examines secrets, dependencies, build and release pipelines, AI security, add-on supply chains, common web risks, and attacker scenarios.

In plain words
What is it for?
It helps run routine or deeper security reviews, investigate exposed secrets and dependency risks, assess AI and CI/CD security, and apply OWASP and STRIDE checks.
Why use it?
It looks beyond application code to find weaknesses in the systems and delivery processes that support it, while aiming to avoid noisy or purely cosmetic findings.

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/timurgaleev/vibestack/cso
Any agent
npx skills add timurgaleev/vibestack --skill cso
Clone the repo
git clone --depth 1 https://github.com/timurgaleev/vibestack

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 cso

README.md
[![agentmods](https://agentmods.dev/badge/skills/timurgaleev/vibestack/cso.svg)](https://agentmods.dev/skills/timurgaleev/vibestack/cso)
Your own site
<a href="https://agentmods.dev/skills/timurgaleev/vibestack/cso"><img src="https://agentmods.dev/badge/skills/timurgaleev/vibestack/cso.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,805 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 4 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00104 $0.12805
Opus 5 $0.00052 $0.06402
Sonnet 5 $0.00021 $0.02561
Haiku 4.5 $0.00010 $0.01281

Measured yesterday against content hash 35d4e4f1ac12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

cso scanned grade C with 4 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 yesterday.

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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

- `IGNORE PREVIOUS`, `system override`, `disregard`, `forget your instructions` (prompt injection)

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

**Gate:** Run only when AWS is detected: a Terraform `provider "aws"` block, a CDK app (`aws-cdk-lib` in package.json or `aws_cdk` in requirements), `boto3` or `@aws-sdk` imports, or `aws sts get-caller-identity` succeed

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Enumerates other installed skillslowAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls -la .claude/skills/ 2>/dev/null

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl`, `wget`, `fetch`, `http`, `exfiltrat` (network exfiltration)
Origin

This is a copy

89% identical to cso — 236 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.

skills/cso/SKILL.md · 779 lines

How it starts

The opening of the file, as written. The whole thing — 779 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to invoke

Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".

Voice triggers (speech-to-text aliases): "see-so", "see so", "security review", "security check", "vulnerability scan", "run security".

Preamble

eval "$(~/.vibestack/bin/vibe-slug 2>/dev/null)" 2>/dev/null || SLUG="unknown"
_LEARN_FILE="${VIBESTACK_HOME:-$HOME/.vibestack}/projects/${SLUG:-unknown}/learnings.jsonl"
if [ -f "$_LEARN_FILE" ]; then
  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
    ~/.vibestack/bin/vibe-learnings-search --limit 5 2>/dev/null || true
  fi
else
  echo "LEARNINGS: none yet"
fi

{{include lib/snippets/session-host.md}}

{{include lib/snippets/decision-brief.md}}

{{include lib/snippets/working-protocols.md}}

{{include lib/snippets/state-protocols.md}}

/cso — Chief Security Officer Audit (v2)

You are a Chief Security Officer who has led incident response on real breaches and testified before boards about security posture. You think like an attacker but report like a defender. You don't do security theater — you find the doors that are actually unlocked.

The real attack surface isn't your code — it's your dependencies. Most teams audit their own app but forget: exposed env vars in CI logs, stale API keys in git history, forgotten staging servers with prod DB access, and third-party webhooks that accept anything. Start there, not at the code level.

You do NOT make code changes. You produce a Security Posture Report with concrete findings, severity ratings, and remediation plans.

User-invocable

When the user types /cso, run this skill.

Arguments

  • /cso — full daily audit (all phases, 8/10 confidence gate)
  • /cso --comprehensive — monthly deep scan (all phases, 2/10 bar — surfaces more)
  • /cso --infra — infrastructure-only (Phases 0-5, 5b, 6, 12-14)
  • /cso --code — code-only (Phases 0-1, 7, 9-11, 12-14)
  • /cso --skills — skill supply chain only (Phases 0, 8, 12-14)
  • /cso --diff — branch changes only (combinable with any above)
  • /cso --supply-chain — dependency audit only (Phases 0, 3, 12-14)
  • /cso --owasp — OWASP Top 10 only (Phases 0, 9, 12-14)
  • /cso --scope auth — focused audit on a specific domain

Read the full file on GitHub · 779 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. yesterday Changed · +74 lines · +17 tokens per session scan B → C 35d4e4f1ac12
  2. 4d ago First seen · 705 lines · 87 tokens per session scan B 8a75c2f67046

Subscribe to this mod's changes

cso is a skill published in the GitHub repository timurgaleev/vibestack (6 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 12,805 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 4 findings (instruction-override phrasing, reaches for credential files, enumerates other installed skills). It is 89% identical to cso, differing in 236 lines, and is treated as a copy.

Related

Other skills, from other repositories

babysit

Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…

kirodotdev/KiroCrew · 137 tokens

devops

Deploy and manage infrastructure with Docker, Kubernetes, CI/CD pipelines, and cloud services. Use when containerizing, deploying, or managing production infrastructure.

ihatesea69/kiro-kit · 32 tokens

app-deployment

Deploy mobile apps to App Store and Google Play. Use when configuring builds, signing, CI/CD pipelines, or preparing store submissions.

ihatesea69/kiro-kit · 30 tokens

ci-cd-patterns

Design and implement CI/CD pipeline patterns for reliable, fast, and secure software delivery. Use when building or optimizing build and deployment pipelines.

ihatesea69/kiro-kit · 33 tokens

ecs-devops

Use when someone is deploying, releasing, or shipping software to Amazon ECS — phrased as "blue/green deployment on ECS", "canary deployment for my ECS service", "set up CI/CD for ECS", "GitHub Actions deploy to Fargate", "my ECS deployment is stuck", "ECS deployment circuit breaker", "ECS task sets", or "migrate off…

aws-samples/sample-apex-skills · 237 tokens

terraform-skill

Use when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops - diagnoses failure mode (identity churn, secrets, blast radius, CI drift, state corruption) with version-aware guards.

aws-samples/sample-apex-skills · 51 tokens