Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aiappsgbb/awesome-gbbnpx agentmods add skills/aiappsgbb/awesome-gbb/paygo-ptu-cost-analyzerWrote 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/aiappsgbb/awesome-gbb/paygo-ptu-cost-analyzer)<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/paygo-ptu-cost-analyzer"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/paygo-ptu-cost-analyzer/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/aiappsgbb/awesome-gbb/paygo-ptu-cost-analyzer"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/paygo-ptu-cost-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 104 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00199 | $0.03582 |
| Opus 5 | $0.00100 | $0.01791 |
| Sonnet 5 | $0.00040 | $0.00716 |
| Haiku 4.5 | $0.00020 | $0.00358 |
Grade A, and why
paygo-ptu-cost-analyzer 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 11d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PAYGO vs PTU Cost Analyzer
Headless cost-analysis skill for Azure OpenAI. Given a window of per-minute token usage, it computes the percentile TPM envelope, prices both PAYGO and PTU scenarios per percentile, estimates spillover costs, and emits a markdown + JSON + PNG report.
This is the analysis core of aiappsgbb/ptu-paygo-mix wrapped in a CLI; the upstream Streamlit UI is excluded by design (this skill runs in a terminal, in CI, or inside an agent — never as a web app).
Sister capability. If you actually want the interactive UI, use the upstream repo directly (
uv run streamlit run app/streamlit_app.py). This skill is for the cases where the seller / analyst / agent needs a report file — over chat, in a PR, or as part of an automated capacity-planning rollup.
Continuous monitoring companion.
foundry-cost-monitoringconsumes live OTelgen_ai.usage.*spans for per-agent / per-project cost projection — use it when the FinOps question is "what's my spend right now?" rather than "how should I size PTU?"
Two data paths
| Path | When to use | Auth needed |
|---|---|---|
--csv <path> |
Customer already exported their token usage (e.g. via the upstream docs/sample_kql_queries.md, Excel, Cost Mgmt export). |
None. |
--workspace <id> |
You have direct read access on the Log Analytics workspace ingesting Cognitive Services metrics. | DefaultAzureCredential (az login / managed identity / env vars / VS Code) with Log Analytics Reader on the workspace. |
--synthetic |
Offline demo, regression test, or you need to show the report shape before real data lands. | None. |
All three paths converge on the same run_analysis() and render_report()
so the output contract is identical.
Required CSV schema
| Column | Type | Notes |
|---|---|---|
minute_bin |
datetime (parseable) | Per-minute bucket. |
input_tokens_sum |
int | Total input tokens in the bucket (includes cached). |
cached_tokens_sum |
int | Subset of input_tokens_sum that hit the prompt cache. |
output_tokens_sum |
int | Generated tokens. |
What ships with it
11 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.
- references/analyzer/__init__.py 1.2 KB runs code
- references/analyzer/analysis.py 5.8 KB runs code
- references/analyzer/data.py 6.6 KB runs code
- references/analyzer/formatting.py 1023 B runs code
- references/analyzer/models.json 8.1 KB
- references/queries/active_tokens.kql 1.4 KB
- references/queries/default.kql 1.6 KB
- references/render_report.py 10 KB runs code
- references/run_report.py 7.7 KB runs code
- references/sample_input.csv 10 KB
- references/upstream-pin.md 22 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.
- 11d ago First seen · 277 lines · 199 tokens per session scan A 7690961037d0
paygo-ptu-cost-analyzer is a skill published in the GitHub repository aiappsgbb/awesome-gbb (5 stars, last pushed 4d ago), licensed MIT. It adds 199 tokens to every session and 3,582 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.