cso

cso is a skill for Claude Code from CarbeneAI/Forge. It costs 116 tokens per session (13,076 once invoked), scanned B, a copy of cso, MIT.

A security-audit mode focused on infrastructure, software dependencies, delivery pipelines, AI systems, and common application threats. It includes threat modelling, a method for identifying how systems could be attacked.

In plain words
What is it for?
Use it to audit secrets, dependency supply chains, CI/CD, AI security, skills, and web applications, including OWASP Top 10 and STRIDE reviews.
Why use it?
It helps uncover exposed secrets, unsafe dependencies, weak CI/CD pipelines, and security risks in applications and AI workflows.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Good fit Use it to audit secrets, dependency supply chains, CI/CD, AI security, skills, and web applications, including OWASP Top 10 and STRIDE reviews.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/carbeneai/forge/cso
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.

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

Made for: Claude Code.

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/carbeneai/forge/cso/github.svg)](https://agentmods.dev/skills/carbeneai/forge/cso)
Your own site
<a href="https://agentmods.dev/skills/carbeneai/forge/cso"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/cso/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 cso

Your own site · 80×15
<a href="https://agentmods.dev/skills/carbeneai/forge/cso"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/cso.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,076 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 80% 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 5.1 $0.00116 $0.13076
Opus 5 $0.00058 $0.06538
Sonnet 5 $0.00023 $0.02615
Haiku 4.5 $0.00012 $0.01308

Measured 7d ago against content hash 2d7921a5a84d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

cso scanned grade B with 3 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 7d 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.

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.

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

80% identical to cso — 405 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.

.claude/skills/cso/SKILL.md · 928 lines

How it starts

The opening of the file, as written. The whole thing — 928 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preamble (run first)

_UPD=$(~/.claude/skills/gstack/bin/gstack-update-check 2>/dev/null || .claude/skills/gstack/bin/gstack-update-check 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
mkdir -p ~/.gstack/sessions
touch ~/.gstack/sessions/"$PPID"
_SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
_PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
echo "BRANCH: $_BRANCH"
_SKILL_PREFIX=$(~/.claude/skills/gstack/bin/gstack-config get skill_prefix 2>/dev/null || echo "false")
echo "PROACTIVE: $_PROACTIVE"
echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
echo "SKILL_PREFIX: $_SKILL_PREFIX"
source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
REPO_MODE=${REPO_MODE:-unknown}
echo "REPO_MODE: $REPO_MODE"
_LAKE_SEEN=$([ -f ~/.gstack/.completeness-intro-seen ] && echo "yes" || echo "no")
echo "LAKE_INTRO: $_LAKE_SEEN"
_TEL=$(~/.claude/skills/gstack/bin/gstack-config get telemetry 2>/dev/null || true)
_TEL_PROMPTED=$([ -f ~/.gstack/.telemetry-prompted ] && echo "yes" || echo "no")
_TEL_START=$(date +%s)
_SESSION_ID="$$-$(date +%s)"
echo "TELEMETRY: ${_TEL:-off}"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
mkdir -p ~/.gstack/analytics
echo '{"skill":"cso","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
# zsh-compatible: use find instead of glob to avoid NOMATCH error
for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
  if [ -f "$_PF" ]; then
    if [ "$_TEL" != "off" ] && [ -x "~/.claude/skills/gstack/bin/gstack-telemetry-log" ]; then
      ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true
    fi
    rm -f "$_PF" 2>/dev/null || true
  fi
  break
done

If PROACTIVE is "false", do not proactively suggest gstack skills AND do not auto-invoke skills based on conversation context. Only run skills the user explicitly types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say: "I think /skillname might help here — want me to run it?" and wait for confirmation. The user opted out of proactive behavior.

If SKILL_PREFIX is "true", the user has namespaced skill names. When suggesting or invoking other gstack skills, use the /gstack- prefix (e.g., /gstack-qa instead of /qa, /gstack-ship instead of /ship). Disk paths are unaffected — always use ~/.claude/skills/gstack/[skill-name]/SKILL.md for reading skill files.

If output shows UPGRADE_AVAILABLE <old> <new>: read ~/.claude/skills/gstack/gstack-upgrade/SKILL.md and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If JUST_UPGRADED <from> <to>: tell user "Running gstack v{to} (just updated!)" and continue.

If LAKE_INTRO is no: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the Boil the Lake principle — always do the complete thing when AI makes the marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Then offer to open the essay in their default browser:

open https://garryslist.org/posts/boil-the-ocean
touch ~/.gstack/.completeness-intro-seen

Only run open if the user says yes. Always run touch to mark as seen. This only happens once.

Read the full file on GitHub · 928 lines

Files

What ships with it

2 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.

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. 7d ago First seen · 928 lines · 116 tokens per session scan B 2d7921a5a84d

Subscribe to this mod's changes

cso is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 13,076 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 3 findings (instruction-override phrasing, enumerates other installed skills, makes network calls). It is 80% identical to cso, differing in 405 lines, and is treated as a copy.

Related

Other skills, from other repositories

implementing-devsecops-security-scanning

Integrates Static Application Security Testing (SAST), Dynamic Application Security Testing (DAST), and Software Composition Analysis (SCA) into CI/CD pipelines using open-source tools. Covers Semgrep for SAST, Trivy for SCA and container scanning, OWASP ZAP for DAST, and Gitleaks for secrets detection. Activates for…

xalgorix/xalgorix · 109 tokens

integrating-sast-into-github-actions-pipeline

This skill covers integrating Static Application Security Testing (SAST) tools—CodeQL and Semgrep—into GitHub Actions CI/CD pipelines. It addresses configuring automated code scanning on pull requests and pushes, tuning rules to reduce false positives, uploading SARIF results to GitHub Advanced Security, and…

xalgorix/xalgorix · 84 tokens

scanning-kubernetes-manifests-with-kubesec

Perform security risk analysis on Kubernetes resource manifests using Kubesec to identify misconfigurations, privilege escalation risks, and deviations from security best practices.

xalgorix/xalgorix · 41 tokens

building-devsecops-pipeline-with-gitlab-ci

Design and implement a comprehensive DevSecOps pipeline in GitLab CI/CD integrating SAST, DAST, container scanning, dependency scanning, and secret detection.

xalgorix/xalgorix · 43 tokens

implementing-infrastructure-as-code-security-scanning

This skill covers implementing automated security scanning for Infrastructure as Code (IaC) templates using tools like Checkov, tfsec, and KICS. It addresses detecting misconfigurations in Terraform, CloudFormation, Kubernetes manifests, and Helm charts before deployment, establishing policy-based governance, and…

xalgorix/xalgorix · 81 tokens

integrating-dast-with-owasp-zap-in-pipeline

This skill covers integrating OWASP ZAP (Zed Attack Proxy) for Dynamic Application Security Testing in CI/CD pipelines. It addresses configuring baseline, full, and API scans against running applications, interpreting ZAP findings, tuning scan policies, and establishing DAST quality gates in GitHub Actions and GitLab…

xalgorix/xalgorix · 76 tokens