How it works
The cheapest instruction is the one loaded only when it's needed.
This is the model behind every TokenCheat score and rewrite — for developers who want to know why a rule was flagged, moved, or left alone. To just check your file, run the free audit.
Don't ask only how to make the prompt shorter.
Ask which instructions must be active now and which only need to be discoverable later. The cheapest instruction is the one loaded only when needed, in the smallest form that preserves required behavior.
A build pipeline for agent instructions.
Measurement comes first. Safe transformation and behavioral evidence come before distribution.
Collect. Pull the instruction files, skills, and MCP configs your agents actually load — the real always-on surface, not the intended one.
Separate the framework from the expertise.
Runtime
Session setup, state, host behavior, checkpoints, artifact paths and operating mechanics. Repeated runtime is a strong structural optimization target when evidence is clear.
Policy
Cross-cutting safety, evidence, completeness, interaction and output rules. Share or defer policy only when required behavior remains explicit.
Capability
The domain methodology that makes a skill valuable. tokencheat protects capability aggressively instead of treating every long instruction as waste.
Measure, audit, optimize, validate.
Not every optimization deserves the same trust.
A compiler people can inspect.
Every recommendation should include evidence, confidence, expected context reduction, behavior risk, evaluation requirements and a rollback path. A plan exists before mutation.
Parsing, hashing, exact duplication and manifests should not spend model tokens.
Static context estimates, provider telemetry and behavioral parity are separate evidence classes.
Safety boundaries, destructive-operation gates and downstream contracts are not casually compressed.
Provenance, source commit and optimization plans remain attached to compiled artifacts.