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 Ghiles3232/weckr-sdks --skill weckr-margin-auditgit clone --depth 1 https://github.com/Ghiles3232/weckr-sdksWrote 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/ghiles3232/weckr-sdks/weckr-margin-audit)<a href="https://agentmods.dev/skills/ghiles3232/weckr-sdks/weckr-margin-audit"><img src="https://agentmods.dev/badge/skills/ghiles3232/weckr-sdks/weckr-margin-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/ghiles3232/weckr-sdks/weckr-margin-audit"><img src="https://agentmods.dev/badge/skills/ghiles3232/weckr-sdks/weckr-margin-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 | $0.00094 | $0.01295 |
| Opus 5 | $0.00047 | $0.00647 |
| Sonnet 5 | $0.00019 | $0.00259 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
weckr-margin-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 10d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weckr margin audit
Check whether a pricing model survives LLM costs. Given a set of plans (name and monthly price) and a rough picture of how much AI usage each plan drives, estimate the AI cost of a typical user and a heavy user on each plan, subtract it from the plan price, and flag the plans where the margin is thin or negative.
This audits AI cost margin only: plan price minus model spend. It does not include your other costs (infrastructure, support, payment fees, salaries), so a plan that looks healthy here can still be unprofitable overall. Be explicit about that when you report.
When to use this skill
Use it for a pricing or unit-economics question spanning plans, not a single feature:
- Which of my plans lose money once I count AI cost.
- Is a flat or unlimited plan sustainable at this price.
- How much of my $29 plan is eaten by model spend.
- Do my price points cover Opus, or should heavy users be on a cheaper model.
For a single feature's cost use weckr-cost-estimator. For a raw price lookup use weckr-model-pricing. To measure the real per user distribution in production instead of estimating, use weckr-integration to wire in Weckr.
How to audit
Show your work so the user can challenge assumptions.
-
List the plans. For each: name, monthly price, and any usage limit. Note which plans are flat or unlimited, since those carry the tail risk.
-
Model the users. For each plan estimate AI usage for a typical user and a heavy user: the model in use, tokens per call, and calls per month. If usage is unknown, assume a shape and say so. The heavy user matters most, because flat pricing is sunk by the tail, not the average.
-
Cost each user. Use current per-million prices, ideally fetched live from
https://useweckr.com/pricing.json(or theweckr-model-pricingskill as fallback), and:ai_cost_per_user_month = calls * ( input_tokens / 1e6 * input_price + output_tokens / 1e6 * output_price ) -
Compute margin per plan. For both the typical and the heavy user:
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.
- 10d ago First seen · 80 lines · 94 tokens per session scan A 438911a2631c
weckr-margin-audit is a skill published in the GitHub repository Ghiles3232/weckr-sdks (8 stars, last pushed 17d ago), licensed MIT. It adds 94 tokens to every session and 1,295 once invoked, about $0.0005 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.