Borrowing it
Nothing to install: this file belongs to DuqueOM/ML-MLOps-Portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DuqueOM/ML-MLOps-Portfolio/main/.devin/skills/cost-audit/SKILL.mdgit clone --depth 1 https://github.com/DuqueOM/ML-MLOps-PortfolioWrote 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/duqueom/ml-mlops-portfolio/cost-audit)<a href="https://agentmods.dev/skills/duqueom/ml-mlops-portfolio/cost-audit"><img src="https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/cost-audit/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/duqueom/ml-mlops-portfolio/cost-audit"><img src="https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/cost-audit.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 | $0.00013 | $0.01087 |
| Opus 5.5 | $0.00005 | $0.00435 |
| Sonnet 5.5 | $0.00003 | $0.00217 |
| Haiku 4.5 | $0.00001 | $0.00109 |
Grade A, and why
cost-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Audit
Step 1: Collect Current Costs
GCP
gcloud billing accounts list
gcloud billing budgets list --billing-account={ACCOUNT_ID}
# Or use the billing export in BigQuery
AWS
aws ce get-cost-and-usage \
--time-period Start=$(date -d '30 days ago' +%Y-%m-%d),End=$(date +%Y-%m-%d) \
--granularity MONTHLY \
--metrics BlendedCost \
--group-by Type=DIMENSION,Key=SERVICE
Step 2: Cost Breakdown by Category
Compute serving (N APIs × 2 clouds): $___/mo
Compute training (Spot, monthly avg): $___/mo
Databases (Cloud SQL + RDS): $___/mo
Storage (GCS + S3): $___/mo
Registry (Artifact Registry + ECR): $___/mo
Monitoring and Logging: $___/mo
TOTAL: $___/mo
Step 3: Check FinOps Rules
| Rule | Status | Action if Violated |
|---|---|---|
| Training on Spot/Preemptible | ✅/❌ | Switch to spot instances (70% savings) |
| Serving on On-Demand | ✅/❌ | Do not change — availability required |
| CPU-only HPA (no idle pods) | ✅/❌ | Fix HPA to avoid over-provisioning |
| Lifecycle policies on buckets | ✅/❌ | Archive after N days, delete after M |
| Budget alerts at 50%/90% | ✅/❌ | Configure in Terraform |
| Non-prod clusters destroyed | ✅/❌ | terraform destroy -var-file=staging.tfvars |
Step 4: Identify Optimization Opportunities
- Right-sizing: Check if node pool machine types match actual usage
- Committed use: If stable baseline, consider 1-year CUDs (30% savings)
- Storage tiering: Move infrequently accessed data to Nearline/Glacier
- Image cleanup: Delete old container images past retention period
- Unused resources: Check for orphaned disks, IPs, load balancers
Step 5: Update Documentation
Update the TCO section in service READMEs and relevant ADRs with:
- Real measured costs (not estimates)
- Date of measurement
- Comparison with previous period
- Optimization actions taken and their impact
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.
- 2mo ago First seen · 120 lines · 13 tokens per session scan A a1d779937e18
cost-audit is a skill published in the GitHub repository DuqueOM/ML-MLOps-Portfolio (7 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 1,087 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
cost-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cost-auditDuqueOM/ML-MLOps-Portfolio | Skill | 7 | yesterday | MIT | A | 13 | Claude Code |
| ecspressokayac/ecspresso | Skill | 1.1k | yesterday | MIT | A | 17 | Claude Code |
| 04-securityskillmds/skillmd | Skill | 189 | 3d ago | MIT | A | 36 | Claude Code |
| eos-cost-analysisaws/tools-for-devops-agent | Skill | 137 | yesterday | Apache-2.0 | A | 215 | Claude Code, Codex |
| geoserver-cloudznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 86 | Claude Code, Codex |
| finopsnitinjain999/platform-skills | Skill | 71 | yesterday | Apache-2.0 | A | 136 | Claude Code |
| cost-checkrshade/finfocus | Skill | 11 | today | Apache-2.0 | A | 131 | Claude Code, Codex |