Insert config · unlock the Cheat Code

Find your agent'sCheat Code.

Your AI coding assistant reads a hidden instruction file on every request. TokenCheat checks it, shows what it costs, and hands you a cleaner version — free, in your browser.

For developers: scores CLAUDE.md, AGENTS.md, .cursorrules and MCP configs for duplicated, stale and always-on rules. Same engine as the CLI.

Run free auditSee the token breakdown
Runs in your browserNo signupNo source upload
TokenCheat // context console

Cheat code generated

agent-instructions.tc

Before

3,820

after 1,140

Tokens saved

2,680

Illustrative active-context estimate

01DROPPaste or select your agent instructions
02SCANFind duplicated, stale, and always-on rules
03PLAYApply the tested Cheat Code
Stage clearBEHAVIOR PRESERVED
Works with // agent CLIs
Claude Code$ claude
OpenAI Codex CLI$ codex
Google Gemini CLI$ gemini
GitHub Copilot CLI$ copilot
Cursor Agent$ cursor-agent
Kiro CLI$ kiro
SYS 0145models with verified per-million pricing
SYS 0253dated price snapshots, committed to git
SYS 0319free tools, running in your browser
SYS 04Approximately 30,237,423tokens saved in our own testing — estimated, not customer-reported
Recognise any of these?

The instructions drifted. The agent did not tell you.

None of these announce themselves. They show up as an agent that used to be reliable and now needs watching — which reads as the model getting worse, not as the instructions around it accumulating.

  • WARN 01Important rules get ignored.
  • WARN 02Different coding agents receive different policies.
  • WARN 03Old project decisions stay loaded forever.
  • WARN 04Destructive actions have no clear approval boundary.
  • WARN 05The same instruction appears in several files.
  • WARN 06Nobody can explain why a rule activated.
  • WARN 07Shortening an instruction file quietly removes capability.
What you can do here

Three jobs. All free, all in your browser.

No signup, and pasted text never leaves your machine. Pick the question you came with.

Check my setup

Is my agent's instruction file bloated or contradictory?

Paste the file your coding agent reads on every request — CLAUDE.md, AGENTS.md, .cursorrules, or an MCP config. Get a score, the exact lines that waste context, and a cleaner version to review.

Run the free audit

Estimate my cost

What will this cost, and which model is cheapest?

Turn tokens into dollars with dated, sourced prices for every major model. Paste text to count tokens, or project a month of Claude Code sessions.

Open the cost calculator

Standardize my agents

How do I give Claude Code, Cursor and Copilot the same rules?

Answer eleven plain-language questions and get one reviewed rulebook — a Cheat Code — exported for each agent you use. Runs locally; nothing is uploaded.

Build a Cheat Code
All 19 free tools How the engine works
Inside the product

The workspace the founding cohort gets.

Saved audit history, context scores over time, and a compiler that turns findings into conservative optimizations. Explore the screens — this is a live preview with illustrative data, not the product API.

Join the founding waitlist
tokencheat workspace — previewillustrative data

Saved audits

24

Average context score

71

Best efficiency score

94

Est. monthly savings

$412

ReportScoreSavings

claude-code · CLAUDE.md

Aug 18

88$96

cursor rules · monorepo

Aug 16

72$54

support-agent system prompt

Aug 14

64$131

mcp servers · 6 enabled

Aug 12

51$88

review-bot instructions

Aug 09

77$43
Pricing

Free today. Founding pricing for the waitlist.

Every tool on this site is free to use in your browser today. Paid plans — saved reports, API and CLI access, team governance — open to the founding waitlist first, at founding pricing locked in before public launch.

Join the founding waitlist
FAQ

What tokencheat means by optimization.

Is tokencheat just a prompt minifier?+

No. tokencheat optimizes context exposure: what must be active now, what can be discovered on demand, what belongs in references, and what is truly waste. Shorter text matters only if required behavior survives.

What is Context Exposure Reduction?+

It compares typical active instruction context before and after an architectural change. It remains an estimate until provider-reported usage is measured, so estimated, measured and behavioral claims stay separate.

What is the Instruction Architecture Score?+

A diagnostic composite of always-on efficiency, duplication, progressive disclosure, trigger specificity, cohesion, portability, freshness, tool overhead, provenance and validation coverage. It is not a promise of causal dollar savings.

Will tokencheat rewrite third-party skills automatically?+

Not by default. Early optimization is conservative and structural. Unknown or restrictive licenses remain analysis-only for public distribution, and semantic changes require evaluation before an Optimized label.

Is the marketplace the main product?+

No. Measurement, compilation, validation and provenance come first. Distribution is the output of a trustworthy build system, not the starting point.

Audit the architecture before you add more context.

Start with your always-on agent config, then extract reusable workflows into portable skills.

Run the config audit →Open Skill Compiler