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 manishiitg/coding-agent-loop --skill cost-anomaly-to-verified-savingsgit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/cost-anomaly-to-verified-savings)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/cost-anomaly-to-verified-savings"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/cost-anomaly-to-verified-savings/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/manishiitg/coding-agent-loop/cost-anomaly-to-verified-savings"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/cost-anomaly-to-verified-savings.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 | $0.00026 | $0.00755 |
| Opus 5.5 | $0.00010 | $0.00302 |
| Sonnet 5.5 | $0.00005 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
cost-anomaly-to-verified-savings 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 20d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Anomaly to Verified Savings
Outcome
Explain a cloud-cost change, prepare an optimization decision, and verify resource savings from comparable billing and health evidence.
When to use
Use for an authorized cloud account and resource with billing and utilization evidence. Start read-only when change or post-change evidence is absent. Use distinct Cost, Delivery and Finance Crews.
Discovery and user direction
Inspect existing Crews, cost basis, resource and finance sources, and IaC ownership. Propose Cost Analyst, Delivery Coordinator and Finance Analyst bindings. Show handoffs, validators, approvals and manual first case. Record customer direction before configuration. Installation approves no change.
Required inputs
Confirm provider, account, service, resource, environment, currency, cost basis, equal periods, owners, reliability policy, IaC route and Finance verification rule. An export supports read-only review. Record missing access.
Plan and AgentWorks tools
Cost Analyst saves cloud-cost-review/v1; run its blocking validator. Delivery Coordinator reads that exact artifact and saves cloud-change-review/v1; validate it before Finance reads. Finance Analyst saves cloud-savings-readout/v1 with pending_change, pending_verification or verified; validate before reporting. Builder supplies paths and repairs any missing validator step. Run one bounded manual case first, then propose a paused recurrence. A separately approved action may prepare or apply an IaC change after fresh state checks.
Knowledge and persistence
Keep stable review, candidate, change and readout IDs, source revisions, Crew runs, artifact paths, validator results, owner decisions and next checks. Re-read billing and resource state on repeat runs. Keep projected, implemented and verified amounts separate, and prevent overlapping candidates from being counted twice.
Validation and reporting
Run scripts/validate_handoff.py cost <cost.json>, then change <cost.json> <change.json>, then savings <cost.json> <change.json> <savings.json> as blocking Workflow steps. Recompute usage, price and one-time effects; join exact provider/account/service/resource/environment and candidate IDs. Deployment needs distinct risk, approval, plan, provider and health receipts. Verified savings need complete equal billing windows, the same basis, comparable workload and observed health. The dashboard shows cost drivers, candidate range, change state, pending evidence and verified resource savings; it never treats an estimate as realized.
What ships with it
22 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.
- examples/cloud-change-deployed.json 1.4 KB
- examples/cloud-change-review.json 1003 B
- examples/cloud-cost-review.json 1.9 KB
- examples/cloud-savings-pending.json 984 B
- examples/cloud-savings-verified.json 1.9 KB
- examples/invalid-cloud-savings-verified.json 999 B
- examples/optimization-candidate.json 1.6 KB
- playbook.json 6.7 KB
- references/finops-workflow.md 7.0 KB
- references/provider-adapters.md 1.9 KB
- references/service-cost-analysis.md 3.0 KB
- references/services/compute.md 1.6 KB
- references/services/databases.md 1.5 KB
- references/services/kubernetes.md 1.5 KB
- references/services/network.md 1.4 KB
- references/services/observability-and-managed-services.md 1.5 KB
- references/services/serverless.md 1.3 KB
- references/services/storage.md 1.5 KB
- references/team-and-handoffs.md 3.8 KB
- scripts/test_validate_handoff.py 3.8 KB runs code
- scripts/validate_handoff.py 14 KB runs code
- SETUP.json 3.5 KB
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.
- 20d ago Changed · -1 lines · -23 tokens per session aa383d1518fd
- 1mo ago First seen · 51 lines · 49 tokens per session scan A 0e0c6b5a2eea
cost-anomaly-to-verified-savings is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 26 tokens to every session and 755 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 2026-09-14.
Other skills, from other repositories
agency-finops-engineer
Expert cloud cost engineer for AWS/GCP/Azure — cost allocation and tagging, rightsizing, commitment planning (reserved instances/savings plans), egress and storage optimization, and unit-economics dashboards that tie spend to business value.
gridcraft
Headless spreadsheets with GridCraft (XLSX/CSV/TSV workbooks, formula evaluation, recalculation, PDF export), provisioned on demand by pi-craft. Use for "build a budget spreadsheet with formulas", "convert this xlsx to csv", "what does this formula evaluate to", "change a cell and recalculate the totals", "export the…
compute-resell
Autonomous compute-reselling agent on Surplus Intelligence - resells free or low-cost provider compute across Bankr, AWS Bedrock, and Google Vertex (GCP) as one skill. Reads the live market + your cost + your usage, auto-lists your models per enabled provider, and reactively prices each offer to win routing within a…
openhermit-admin
Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
CloudCostOptimizer
Complete FinOps and cloud cost intelligence — AWS/GCP/Azure cost optimization, reserved instance strategy, rightsizing, spot instances, cost allocation, and achieving 30-60% cloud savings without sacrificing reliability.