agent-bom-discover-gcp

agent-bom-discover-gcp is a skill for Claude Code, Codex from msaad00/agent-bom. It costs 77 tokens per session (1,014 once invoked), scanned C, original, Apache-2.0.

A discovery workflow for finding Google Cloud resources used by AI agents or MCP systems, including Vertex AI, Cloud Run, Cloud Functions, and GKE. It produces a standard inventory file and can optionally scan that inventory for findings.

In plain words
What is it for?
Use it to inventory approved GCP projects with read-only access, save canonical inventory JSON, and run an agent-bom scan when findings are requested.
Why use it?
It creates a documented, schema-checked view of relevant cloud assets without handing long-lived credentials to the scanning tool or changing resources.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to inventory approved GCP projects with read-only access, save canonical inventory JSON, and run an agent-bom scan when findings are requested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/msaad00/agent-bom/discover-gcp
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 msaad00/agent-bom --skill discover-gcp
Clone the repo
git clone --depth 1 https://github.com/msaad00/agent-bom

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 agent-bom-discover-gcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/msaad00/agent-bom/discover-gcp/github.svg)](https://agentmods.dev/skills/msaad00/agent-bom/discover-gcp)
Your own site
<a href="https://agentmods.dev/skills/msaad00/agent-bom/discover-gcp"><img src="https://agentmods.dev/badge/skills/msaad00/agent-bom/discover-gcp/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 agent-bom-discover-gcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/msaad00/agent-bom/discover-gcp"><img src="https://agentmods.dev/badge/skills/msaad00/agent-bom/discover-gcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,014 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00077 $0.01014
Opus 5 $0.00039 $0.00507
Sonnet 5 $0.00015 $0.00203
Haiku 4.5 $0.00008 $0.00101

Measured today against content hash 413840d3ac9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

agent-bom-discover-gcp scanned grade C with 1 finding 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 today.

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.

Reaches for credential fileshighPrivilege escalation

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

- "~/.config/gcloud/application_default_credentials.json"
integrations/openclaw/discover-gcp/SKILL.md · 113 lines

What it actually says

agent-bom-discover-gcp

Use this skill to collect GCP AI and workload inventory as schema-valid agent-bom inventory. Default to discover-only: write JSON to an operator-selected path and stop.

Guardrails

  • Use only operator-approved projects and read-only credentials.
  • Do not request or display service account private keys, OAuth refresh tokens, or bearer tokens.
  • Do not modify GCP resources. This workflow is discovery-only.
  • Write inventory only to a path the operator chose.
  • Treat AI-generated prose as non-authoritative; schema-validated inventory JSON is the evidence.

Workflow

python examples/operator_pull/gcp_inventory_adapter.py \
  --project "$GOOGLE_CLOUD_PROJECT" \
  --region us-central1 \
  --source gcp-skill-invoked \
  --discovery-method skill_invoked_pull \
  --output gcp-inventory.json

Scan only when the operator asks for findings:

agent-bom scan --inventory gcp-inventory.json --format json --output agent-bom-gcp-findings.json

Evidence Contract

The emitted inventory carries discovery_provenance.source_type: skill_invoked_pull, observed_via: skill_invoked_pull, gcp_sdk, sanitized metadata.permissions_used, and redacted credential material. If schema validation fails, stop and fix the inventory instead of scanning a best-effort summary.

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. today Changed 413840d3ac9b
  2. 5d ago Changed 404bc1b25623
  3. 9d ago First seen · 113 lines · 77 tokens per session scan C 66d169948253

Subscribe to this mod's changes

agent-bom-discover-gcp is a skill published in the GitHub repository msaad00/agent-bom (31 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 1,014 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.