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.
npx skills add shivamsriva31093/gcp-ironclad --skill gcp-spend-cap-setupgit clone --depth 1 https://github.com/shivamsriva31093/gcp-ironcladWrote 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.
[](https://agentmods.dev/skills/shivamsriva31093/gcp-ironclad/gcp-spend-cap-setup)<a href="https://agentmods.dev/skills/shivamsriva31093/gcp-ironclad/gcp-spend-cap-setup"><img src="https://agentmods.dev/badge/skills/shivamsriva31093/gcp-ironclad/gcp-spend-cap-setup/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.
<a href="https://agentmods.dev/skills/shivamsriva31093/gcp-ironclad/gcp-spend-cap-setup"><img src="https://agentmods.dev/badge/skills/shivamsriva31093/gcp-ironclad/gcp-spend-cap-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.02189 |
| Opus 5 | $0.00049 | $0.01094 |
| Sonnet 5 | $0.00020 | $0.00438 |
| Haiku 4.5 | $0.00010 | $0.00219 |
Grade A, and why
gcp-spend-cap-setup scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://billingbudgets.googleapis.com/\$discovery/rest?version=v1" \ How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCP Spend-Cap Setup (GUIDED)
Overview
Google's spend caps on budgets (Public Preview since 2026-07-29) actually pause a service when a monthly threshold is hit — but creation is console-only: the Billing Budget API v1 has no enforcement field and gcloud billing budgets create has no cap flag. This skill is therefore GUIDED: it runs only read-only commands itself; you perform the single mutation in the console; the skill prepares everything before and verifies everything after.
A tripped cap returns permission errors (403) to ALL callers of that service, including production. Choosing to cap is a human decision — that is by design.
When to Use
- Standalone, whenever you want hard caps on AI/serverless spend.
- After a
gcp-ironcladrun: the final report'srecommend_spend_capflags point here. - During an active incident. Unlike the APPLY skills, there is no bleeding-halt gate — a spend cap is precisely the emergency brake, so this skill must work while a project is bleeding.
Inputs
SESSION_DIRenv var — session directory; create/tmp/gcp-ironclad/<iso-ts>/if unset (same convention as the other skills).MODEenv var — unset for a full run;verifyto skip to Step 4 using a prior${SESSION_DIR}/spend-caps.json.- No
DRY_RUN: the skill never mutates, so there is nothing to dry-run.
Outputs
${SESSION_DIR}/spend-caps.json— matchesoutput.schema.json, self-validated at the end.${SESSION_DIR}/spend-cap-runbook.md— the console runbook, kept for audit trail.
Execution
Step 0 — Preflight + API-surface probe
- Print the active CLI and ADC identities so a mismatch is visible before anything silently 403s:
If the ADC identity is known to differ from the CLI identity, warn: ADC is a separate login; a mismatch produces silent PERMISSION_DENIED on API calls.gcloud auth list --filter=status:ACTIVE --format="value(account)" gcloud auth application-default print-access-token >/dev/null 2>&1 || echo "WARN: no ADC credentials — run: gcloud auth application-default login" - Probe the Budget API surface for future enforcement support:
curl -s "https://billingbudgets.googleapis.com/\$discovery/rest?version=v1" \ | jq -r '.schemas.GoogleCloudBillingBudgetsV1Budget.properties | keys[]' \ | grep -iE "enforce|cap|pause" || true- No match (today's state) →
apiSurfaceDetected: false. - Any match →
apiSurfaceDetected: true; print: "Budget API now exposes an enforcement-like field — Google may have shipped API support for spend caps. This skill predates that; check the docs and consider upgrading it. Continuing in guided mode." Do NOT attempt to use the field.
- No match (today's state) →
What ships with it
1 file 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.
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.
- 12d ago First seen · 125 lines · 98 tokens per session scan A 83bae105f219
gcp-spend-cap-setup is a skill published in the GitHub repository shivamsriva31093/gcp-ironclad (24 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 2,189 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
finops-expert
Expert-level cloud financial operations, cost optimization, and cloud economics. Use when the user mentions cloud cost, optimization, cloud economics, or AWS cost, or when the task involves FinOps Fundamentals, Cost Management, FinOps Practices, or Cost Visibility.
recipes
Use when a user states a FinOps outcome rather than a tool. Route to one recipe card, then hand off: bill jump → explain-period-change (DIGEST preview); marketplace → marketplace-spend; K8s namespace → namespace-cost; credits runway → provider-credits; GCP spend CUD leftover → gcp-spend-cud; BigQuery warehouse →…
gcp-expert
Expert-level Google Cloud Platform, services, and cloud architecture. Use when the user mentions Google Cloud, Cloud Functions, BigQuery, or Firestore.
dashboards
Use when creating or extending Costory dashboards, generating interesting FinOps overviews (suggestgroupby + suggestusagemetrics + text widgets), adding or replacing widgets, copying widgets between dashboards, editing dashboardContext (global filter / period / groupBy) via updatedashboard, or applying shared-context…
query
Use when exploring Costory cost, usage, metric, formula, budget, or external-metric data with the query tool — scope vs split (filterCel / groupBy), explorer PoP comparison, CEL discovery, unit economics, budgets. Not for one-shot "what changed last month" change trees — those use recipes explain-period-change /…
cost-change-investigation
Use when investigating a cost change to explain what changed, when, and the best-supported drivers with contribution, timing, usage, metric, event, alert, and terminology evidence. Call getskill with skillId "cost-change-investigation" before starting the investigation.