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 jxoesneon/Ciel --skill billing-and-burn-opsgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/billing-and-burn-ops)<a href="https://agentmods.dev/skills/jxoesneon/ciel/billing-and-burn-ops"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/billing-and-burn-ops/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/jxoesneon/ciel/billing-and-burn-ops"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/billing-and-burn-ops.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 | $0.00020 | $0.00507 |
| Opus 5 | $0.00010 | $0.00253 |
| Sonnet 5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
billing-and-burn-ops 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 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.
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.
What it actually says
CIEL ADAPTATION: Billing & Burn Ops (The Value Layer)
This skill formalizes the auditing of system costs and revenue integrity. it prioritizes code-backed truth and identifying high-burn failure patterns.
Burn Auditing (ECC Tools)
- Trace Ingress: Map every webhook -> queue -> worker path before suggesting fixes.
- Recursion Risk: Treat app-generated branches/PRs as priority-0 recursion risks.
- Premium Leakage: Verify if capped/free users are hitting premium analyzers (e.g., Opus).
- Retry Burn: Fix deterministic failures that waste tokens on repeated non-transient errors.
Revenue & Pricing Truth
- Paid Sales: Rely ONLY on live billing data or timestamped snapshots.
- Product Truth: Inspect the entitlement code path. PROHIBIT assuming "team billing" exists just because it's in the marketing copy.
- Customer Impact: Distinguish between accidental duplicates and deliberate multi-seat intent before refunding.
Decision Format
Every audit MUST end with:
- Snapshot: Timestamped revenue/anomalies.
- Product Truth: What the code actually does vs marketing claims.
- Decision: Refund, Preserve, or No-op.
- Gap: The exact backlog item required to fix the workflow.
Anti-Patterns
- Diagnosis via Marketing: Claiming a feature works because it's on the landing page.
- Refund-First: Refunding without classifying the issue, losing valuable intent data.
- Expensive Failure: Spending $50 in tokens only to fail on a file-push conflict.
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.
- 7d ago First seen · 54 lines · 20 tokens per session scan A a6247ddc86b9
billing-and-burn-ops is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 20 tokens to every session and 507 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other skills, from other repositories
gumroad-support-refund-request
Handle buyer refund requests on Gumroad — standard, subscription, and duplicate-charge cases. Use when a ticket asks for money back, reports a double charge, or a seller is unresponsive to a refund. Decides eligibility, executes, and replies.
api-usage-biller
Usage-based pricing is hard to track. This agent processes a raw log of API calls, sums them by CustomerID, calculates overage fees based on their plan limit, and generates a billing CSV.
stock-analyzer
A comprehensive stock deep analysis tool that combines real-time quotes, fundamental metrics, technical indicators, and growth analysis into a single professional report. Supports A-share, US stocks, HK stocks. Generates detailed investment recommendations with risk assessment and actionable trading strategies.
Coinbase Automation
Coinbase Automation: list and manage cryptocurrency wallets, accounts, and portfolio data via Coinbase CDP SDK.
market-research
A guide for conducting market research, including research standards, research modes, and checks on investors or investment funds. The description does not specify its exact outputs or workflow.
Code Quality Review
Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.