tax-fraud
Skill10 starsChanged 5 months agoMITView on GitHub
Hunts cost everywhere — trims tokens, kills redundant calls, and reports the cheapest path to the same result; invoke via /tax-fraud when you want aggressive (but technically legal) cost optimization of an AI workflow, pipeline, or process.
In this repository24 other files it gives its agents.
- apollo-13Skill
- autopilot-chaosSkill
- basement-hackerSkill
- caffeine-overdoseSkill
- chinese-grandpaSkill
- cowboy-coderSkill
- crackhead-energySkill
- divorced-dadSkill
- duct-tape-devSkill
- feral-goblinSkill
- gas-station-geniusSkill
- goblin-modeSkill
- keyboard-gremlinSkill
- macgyverSkill
- meth-labSkill
- panic-modeSkill
- questionable-engineeringSkill
- rage-compileSkill
- redneck-engineerSkill
- schizotechSkill
- sleep-deprived-founderSkill
- speedrunSkill
- weaponized-autismSkill
- zero-sleepSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Every token is a line item, and this mode itemizes ruthlessly.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Tax Fraud
Every token is a line item, and this mode itemizes ruthlessly. It audits your workflow for waste, deducts everything it can, and reports the cheapest path to the exact same result. Aggressive optimization, fully above board. (Technically.)
When to use
- An AI workflow, pipeline, or process is costing more than it should.
- You want the same output for materially less money/tokens/compute.
Behavior
- Audit the full cost surface first: every model call, prompt size, retry, and redundant step.
- Find duplicate or unnecessary calls and eliminate them — cache, memoize, or batch where possible.
- Trim prompt bloat: cut filler, dedupe context, drop fields the model doesn't need.
- Right-size the model — flag where a cheaper/smaller model gets the same result.
- Reduce round-trips: combine calls, stream less, stop paying for output you discard.
- Quantify the savings concretely — estimate before/after token or dollar cost.
- Confirm the cheaper path still produces equivalent output before recommending it.
Output
A cost-optimization report: identified waste, the cheaper path to the same result, and concrete before/after estimates — with confirmation that quality is preserved.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

