Free tools
Every tool here runs free in your browser.
Measure what your agents load, audit the instruction files behind it, and optimize with evidence. Pasted text never leaves your machine.
Agent Config Audit
Score and conservatively optimize always-on agent instruction files in the browser.
Open tool →
Skill Compiler
Start with Prompt → Skill today; inspect the full roadmap for repo audits, structural builds, host packages, provenance, and behavioral validation.
Open tool →
Agent Cheat Code
Compile your durable working conditions, technology policy, and action boundaries into one portable Cheat Code, then export adapters for Claude Code, Cursor, Copilot, and AGENTS.md.
Open tool →
Technology and Action Register
Review all twenty-one capability decisions as one sortable table and every action an agent may take on your behalf, with the authorization level each one sits at. States policy; the host enforces it.
Open tool →
Instruction Stack Optimizer
Audit pasted instructions with the full linter and quality index, then compile a layered policy pack — compact trigger profile plus Claude Code, Cursor, and Copilot exports.
Open tool →
MCP Context Estimator
Estimate standing tool-schema context and repeated context exposure from enabled MCP servers.
Open tool →
AI Token Calculator
Already have token counts? Turn input, output, and cache tokens into cost using maintained per-million pricing. Estimates only — verify against your provider invoice.
Open tool →
Token Counter
Paste text or code and get an estimated token count and cost per model. Use the AI Token Calculator instead when you already have token counts.
Open tool →
Claude Code Cost Estimator
Project Claude Code spend from session shape and model rates, before it lands on an invoice.
Open tool →
Cost Per PR Estimator
Estimate AI spend per merged pull request from session tokens, sessions per PR, and model rates — then weigh it against the time saved.
Open tool →
Prompt Caching Savings Calculator
Model what prompt caching changes for a workload, using each model's published cache-read and cache-write rates.
Open tool →
AI Coding Spend Index
Position your AI coding spend against reference bands for cost, caching, context usage, and audit score. Directional placement, not a survey.
Open tool →
Model Price Comparison
Provider-by-provider view of per-million input and output rates with context windows, sourced from provider pricing pages.
Open tool →
AI Pricing Changelog
Dated log of observed changes to model pricing, cache rates, and context windows. Every entry links the provider page that settles it.
Open tool →
CLAUDE.md Bloat Checker
Score an instruction file in the browser and see exactly which lines cost context without changing behavior.
Open tool →
Repo Context Score
Estimate the tokens an AI pays to read your repo and what structured retrieval could change. Chars/4 heuristic — estimates only.
Open tool →
Instruction Source Classifier
Paste the instruction files your agents load and see what each rule is, where it belongs, what it costs, and which rules repeat across files.
Open tool →
Stack Atlas
Is a library maintained, deprecated, or superseded? Dated RepoFacts for open-source repositories: health with coverage and confidence, npm adoption, momentum, and reviewed successors.
Open tool →
Policy Drift Preview
The ten checks that find where instructions, packages, tools and decisions stop matching your policy — shown as worked examples, with what each needs connected.
Open tool →
Founding waitlist
Keep this analysis. The workspace saves it.
The paid workspace adds saved reports and score history, API and CLI access, and team governance — opening to the founding waitlist first, at founding pricing locked in before public launch. This tool stays free either way.