Case 03767
A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.
npx -y skills add knownasnaffy/prompthound --skill case_03767Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Projects revenue for OpenClaw sub-agent strategies (marketplace, subs, pay-per-task). Use for monetization estimates: input users/pricing/conversions → detailed annual/monthly projections, sensitivity analysis, break-even. Triggers: 'calculate revenue', 'project earnings', 'monetize skill/agent'.
SKILL.md
1.2 KB, as published. Nobody here has run it
Revenue Calculator
Workflow
- Gather Inputs: Users/mo, price ($/user/task), conv rate (%), churn (%), costs (% compute).
- Select Strategy: 1=API Sales, 2=Marketplace, 3=White-label, 4=Affiliates.
- Calculate: Monthly/annual rev, net profit. Use scripts/revenue-calc.py for models.
- Output: Table + sensitivity (e.g., +/-20% users) + next steps.
- Sensitivity: Test scenarios (low/med/high).
Quick Example
Input: Strategy 2, 100 users, $10/mo, 80% conv, 10% churn, 20% costs. Output: Monthly $800, Annual $8,640 net.
Strategies Pricing Defaults (ref/pricing-models.md)
- Sub: $9-99/mo
- Per-task: $0.01-1
- Usage: $0.001/token
- Affiliate: 5-20%
Resources
scripts/revenue-calc.py
Exec for precise calcs (input JSON → output JSON/table).
references/pricing-models.md
Full tables/examples.
assets/report-template.md
Copy for formatted outputs.
Gives 0 of the 12 instructions most pricing monetisation skills give
Counted across 366 of the 366 authors here whose files we hold, read 2026-08-06
- verify webhook signaturesin 23 of 366, across 19 files
- differentiate tiers using features, limits, or supportin 15 of 366, across 4 files
- read product marketing context before asking questionsin 14 of 366, across 6 files
- base price on perceived value, not costin 14 of 366, across 3 files
- use Van Westendorp to find acceptable price rangein 14 of 366, across 3 files
- use MaxDiff to identify highly valued featuresin 14 of 366, across 3 files
- choose a value metric that scales with customer valuein 14 of 366, across 9 files
- handle webhook events idempotentlyin 12 of 366, across 6 files
- understand the upgrade context before recommendingin 11 of 366, across 4 files
- align the pricing metric with delivered valuein 10 of 366, across 4 files
- install stripe packagein 10 of 366, across 5 files
- calculate unit economics metricsin 10 of 366, across 5 files
Said here and by no other author read
- gather required inputs from the user
- calculate monthly and annual net profit
- test low medium and high sensitivity scenarios
- output a formatted projection table
- provide next steps with the output
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.