

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
1# extension — "Caveman Mode" browser extension (MV3, no bundler)23The consumer top-of-funnel: a toggle that, on ChatGPT / Claude / Gemini, prepends the **caveman4skill directive** to each message you send and re-fires the send, so the AI replies in a compact,5high-density style intended to preserve technical substance. It only ever adds text to your *outgoing*6message; it never reads replies, never touches network requests. Savings are `inferred`. (This is7the directive-injector product; an earlier revision shipped a local WASM compress button — EXT8removed it after Chrome Web Store review couldn't reproduce "compress prompt locally".)910## Layout11- `manifest.json` — MV3. `storage` permission only. Content scripts load `src/directive.js` **then** `src/caveman.js` (order matters). Only the fonts are web-accessible — no WASM, no special CSP.12- `src/directive.js` — the **pure** caveman directive text: `buildPrimer`/`buildReminder`/`isPrefixed`/`normLevel`. No chrome/DOM/network. Loaded first (exposes `self.CavemanDirective`) and required directly by the test suite.13- `src/caveman.js` — content script: per-site composer adapter + capture-phase send interception. Prepends the directive (full primer on the first message, short reminder after) and re-fires send. Resilient selectors; safe `setText` (never `textContent=`, which desyncs ProseMirror/Quill); polls for the enabled send button before clicking.14- `src/background.js` — service worker: just reflects the on/off state on the toolbar badge.15- `popup.{html,js,css}` — the on/off toggle, intensity (lite/full/ultra), per-site switches, and a **Leave-a-review** CTA (links to this install's Chrome Web Store reviews via `chrome.runtime.id`).16- `test/` — pure directive/service-worker tests plus real Chromium17 content-script and popup/storage journeys against `harness.html`.1819## Conventions & honesty20- **Edits your outgoing message only.** Prepends a visible directive; never reads model replies, never touches network requests, never automates anything beyond submitting the message you sent.21- **Local-only.** No network requests, no analytics. Stores only `enabled` / `level` / `sites` in `chrome.storage.sync`.22- **Honest about injection.** The directive is plainly visible in the chat — the extension doesn't hide what it adds.23- **inferred-only.** Token savings are an effect of the model's terser replies; never labeled `verified`.2425## Conventions26- Build/test: `npm test` for pure tests; `npm run test:browser` for Chromium send interception, popup storage,27 per-site controls, and review-link behavior. There is no28 build step — MV3 loads the source directly.29- Package: `npm run package` runs both suites, then writes `dist/caveman-browser-<version>.zip`. Staged set uses explicit allowlist in `scripts/verify-extension-stage.mjs`, cross-checked against manifest/CSS/HTML references.30- Composer + send selectors live in the `SITES` map in `src/caveman.js`; a site redesign means updating it (each entry keeps aria-label fallbacks so one rename doesn't break it).3132See ../../CLAUDE.md (root)33
One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| JuliusBrussee/cavemanCLAUDE.md · 98k | CLAUDE.md | archgitdo-notagent-behaviour+1 | 73/100 | today | |
| JuliusBrussee/cavemanagents/AGENTS.md · 98k | AGENTS.md | agent-behaviour | 16/100 | today | |
| JuliusBrussee/cavemanagents/CLAUDE.md · 98k | CLAUDE.md | stylearchsecurityagent-behaviour | 64/100 | today | |
| JuliusBrussee/cavemanbrowse/CLAUDE.md · 98k | CLAUDE.md | testarch | 59/100 | today | |
| JuliusBrussee/cavemancacheengine/CLAUDE.md · 98k | CLAUDE.md | testarch | 73/100 | today | |
| JuliusBrussee/cavemanengine/AGENTS.md · 98k | AGENTS.md | stylearch | 66/100 | today | |
| JuliusBrussee/cavemanengine/CLAUDE.md · 98k | CLAUDE.md | stylearch | 58/100 | today | |
| JuliusBrussee/cavemanextension/AGENTS.md · 98k | AGENTS.md | buildteststylearch+1 | 73/100 | today | |
| JuliusBrussee/cavemanintegrations/CLAUDE.md · 98k | CLAUDE.md | stylearch | 55/100 | today | |
| JuliusBrussee/cavemanmcp/AGENTS.md · 98k | AGENTS.md | stylearch | 79/100 | today | |
| JuliusBrussee/cavemanmcp/CLAUDE.md · 98k | CLAUDE.md | stylearch | 79/100 | today | |
| JuliusBrussee/cavemanmem/AGENTS.md · 98k | AGENTS.md | stylearchperformanceagent-behaviour | 67/100 | today | |
| JuliusBrussee/cavemanmem/CLAUDE.md · 98k | CLAUDE.md | stylearchperformanceagent-behaviour | 71/100 | today | |
| JuliusBrussee/cavemanpackages/agent/CLAUDE.md · 98k | CLAUDE.md | archtesting-strategysecuritydependencies+2 | 34/100 | today | |
| JuliusBrussee/cavemanpackages/cli/AGENTS.md · 98k | AGENTS.md | stylearchdependenciesmonorepo | 71/100 | today | |
| JuliusBrussee/cavemanpackages/cli/CLAUDE.md · 98k | CLAUDE.md | stylearchdependenciesmonorepo | 71/100 | today | |
| JuliusBrussee/cavemanpackages/create-caveman-agent/CLAUDE.md · 98k | CLAUDE.md | archdependenciesmonorepoagent-behaviour | 36/100 | today | |
| JuliusBrussee/cavemanpackages/graders/AGENTS.md · 98k | AGENTS.md | teststylearchtypes+3 | 75/100 | today | |
| JuliusBrussee/cavemanpackages/graders/CLAUDE.md · 98k | CLAUDE.md | teststylearchtypes+3 | 75/100 | today | |
| JuliusBrussee/cavemanpackages/kit/AGENTS.md · 98k | AGENTS.md | stylearchdependenciesmonorepo | 63/100 | today |
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| stacklok/toolhiveCLAUDE.md · 2.0k | CLAUDE.md | buildteststylearch+4 | 100/100 | 14 days ago | |
| Adit-Jain-srm/NightmareNetCLAUDE.md · 46 | CLAUDE.md | buildtestlint-formatstyle+6 | 100/100 | 14 days ago | |
| microsoft/playwrightCLAUDE.md · 95k | CLAUDE.md | buildtestlint-formatstyle+7 | 100/100 | 7 days ago | |
| nimbalyst/nimbalystpackages/android/CLAUDE.md · 1.5k | CLAUDE.md | setupbuildstylearch+2 | 100/100 | 14 days ago | |
| dotCMS/corecore-web/CLAUDE.md · 949 | CLAUDE.md | teststylearchtesting-strategy+3 | 100/100 | 14 days ago | |
| tphakala/birdnet-goCLAUDE.md · 1.6k | CLAUDE.md | buildtestlint-formatstyle+8 | 100/100 | today | |
| tyrchen/geektime-bootcamp-aiw7/genslides/backend/CLAUDE.md · 230 | CLAUDE.md | testlint-formatstylearch+6 | 100/100 | 9 days ago | |
| bagisto/bagistoCLAUDE.md · 28k | CLAUDE.md | setupbuildteststyle+5 | 100/100 | 7 days ago |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/juliusbrussee-caveman-extension-claude)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.