# Consent and Privacy Fix Desk: agent fixes for cookie banners, trackers and privacy policies, checked against the original, owner approved

> Let an agent make your analytics and ad pixels wait for a real choice, fix the cookie banner and bring the privacy policy in line with what your pages load. It writes fixed copies, never the live page. A fix check refuses deleted trackers, edited tracker code, new third-party scripts, removed words and a Reject button smaller than Accept. A policy check catches tools the policy leaves out and retention periods the agent made up. A tested consent.js honors Global Privacy Control. You approve at your terminal and put it live yourself.

- URL: https://paperchasewebb.ai/bots/marketplace/items/consent-privacy-fix-desk-trackers-wait-for-choice-policy-checked-owner-approved/
- Type: Prompt pack
- Category: Solo business
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Grok Bot, Hermes (named in the listing); Plain Markdown files, a small Python checker, a first-party consent.js, and rules for AGENTS.md and CLAUDE.md, Claude Code and Codex notes, Hermes notes and a Grok Bot standing order. The agent files were checked by the checker on Linux; they were not loaded inside each agent for this release
- Price: $29 USD
- Difficulty: Intermediate
- Setup time: 1 hr
- Time to result: The worked example in 5 minutes; your home page scanned and fixed in about an hour
- Format: Markdown (.md) file, consent-privacy-fix-desk-trackers-wait-for-choice-policy-checked-owner-approved.md
- Version: 1.0, updated 2026-11-01
- License: Use inside your own business or on your clients' sites. Do not resell or republish the kit itself.

## What you end up with

Trackers on your pages wait for a choice, Reject is as easy as Accept, and your policy names what your pages actually load, one approved fix at a time, with nothing deleted and no claim that anything is compliant.

## What you get

- 21 sections and an appendix in one .md file, with a one-line unpack for all 67 files
- privacy_check.py scan: 20 checks for trackers that fire before a choice, banner problems, missing opt-out links, Global Privacy Control, unknown scripts and pixels on sensitive pages
- privacy_check.py fix: 17 checks that compare the agent's copy with the original, so fixing by deleting a tracker, editing its code or pasting in a new script fails
- privacy_check.py policy: 12 checks that compare your privacy policy with the trackers your pages load and the retention periods you wrote
- consent.js and a mobile-first banner with matching Reject all and Accept all buttons, tested in a real browser, including Global Privacy Control
- The owner step: approve.py needs a real terminal and part of the file hash, refuses agent sessions and piped input, and checks the live page has not changed since the fix
- A 6-page eval set, rules and two skills for Grok Bot, Claude Code, Codex and Hermes, six prompts and six templates
- The test harness: 75 unit tests, 465 planted faults and a 15-check browser test you can repeat

## Who it is for

Site owners, web teams and agencies running analytics or ad pixels who want an agent to put consent in front of the trackers and keep the policy honest, with a person approving every change.

## Tools needed

- Python 3.8 or newer: runs the page scan, the fix check, the policy check, the report check, the rules and settings checks and the owner approval script; standard library only
- Grok Bot, Claude Code, Codex or Hermes: writes fixed copies of your exported pages and a policy draft under the AGENTS.md rules or the Grok Bot standing order; never edits the site and never approves
- Your page source as HTML files: saved from your CMS, static site folder or build output into site/pages; the kit never logs in to your site
- You need: Python 3.8 or newer
- You need: The HTML source of the pages you want fixed
- You need: A list of the tools your site uses and how long you keep each kind of data
- You need: Someone who approves each fix and puts it live

Cost to run: The kit is the only purchase. Everything runs locally with Python; the checker makes no network calls, logs in to nothing and changes no website.

## How it works

1. **Unpack and test.** Save the kit as pack.md in an empty folder, run the unpack line from Appendix A, then sh test_all.sh. Expected: 67 files written; 75 tests OK; 465 of 465 planted faults caught; the browser test runs too if Playwright is installed.
2. **Watch the flow.** Run sh example/run_example.sh and read it next to section 17. Expected: A coffee roaster's home page with 11 findings, an agent's first-try fix with 13, the second fix clean, the old policy with 15, the drafted policy clean, a first-try report with 4 and a piped approval refused.
3. **Put in your site.** Fill in site/site.json from the template with your tools, categories and retention periods, save your pages into site/pages, then run python3 desk/privacy_check.py site. Expected: No findings, or a short list of settings to fix first.
4. **Fix the home page and the policy.** Run privacy_check.py scan site/pages, have your agent follow skills/consent-fix for the home page and skills/policy-check for the policy, then privacy_check.py fix queue/fixes. Expected: A fixed copy and a policy draft in queue/fixes with 0 high findings, and a report listing what is left for you and what to check by hand.

## Sample prompt: First pass (Grok Bot, Claude Code, Codex, Hermes)

```
Follow skills/consent-fix for site/pages/index.html. Never edit the site. List the codes fixed and the codes left for me, with the reason for each.
```

Prompt 1 of 6.

## Sample prompt: List the tools (Grok Bot, Claude Code, Codex, Hermes)

```
List every third-party script, pixel, frame and form target in site/pages with the page, the domain and whether it is in site.json. Do not edit site.json.
```

Prompt 3 of 6.

## Sample prompt: Draft the policy (Grok Bot, Claude Code, Codex, Hermes)

```
Follow skills/policy-check. Draft queue/fixes/policy.md from templates/privacy-policy-outline.md using only facts in site.json. Where a fact is missing, write a question for me instead.
```

Prompt 4 of 6.

## Free preview of consent-privacy-fix-desk-trackers-wait-for-choice-policy-checked-owner-approved.md

````markdown
# Consent and Privacy Fix Desk: agent fixes for cookie banners, trackers and privacy policies, checked against the original, owner approved

Version 1.0, 2026-11-01. By PaperChaseWebb. For site owners, small businesses, web teams and agencies who want an AI agent to make trackers wait for a real choice, fix the cookie banner and bring the privacy policy in line with what the pages actually load, without deleting trackers, editing tracker code, inventing retention periods, pasting in a consent platform or claiming the site is compliant. Works with Grok Bot, Claude Code, Codex and Hermes. Python 3.8 or newer, standard library only, no API keys, no logins. The kit and the agent never edit your website. Tested with 75 unit tests, 465 planted faults and a 15-check real browser test on Linux with Python 3.13, 3.12, 3.11, 3.9 and 3.8. All business and page data in this kit is made up. Not legal advice.

Most small sites have the same few problems. Google Analytics and an ad pixel fire the moment the page opens. The banner has a big Accept button and a grey "settings" link. It says "by continuing to browse you agree". There is no way to change your mind later, no Do Not Sell or Share link, and nothing reads the Global Privacy Control signal. The privacy policy was copied from a template years ago, names a tool the site dropped and leaves out the three it added since.

Regulators have started acting on exactly this. In 2025 the California Privacy Protection Agency fined a carmaker ove
````

## Test record

- Date: Nov 1, 2026
- What was run: tests/test_scan.py (24), test_fix.py (20), test_policy.py (9), test_modes.py (8), test_approve.py (9, on a real pseudo terminal) and test_mini.py (5); tests/mutate.py with 404 planted faults across page problems, bad fixes, policies, reports, agent rules, site settings, the eval set and approve.py, plus 61 against privacy_mini.py; browser/test_consent_browser.py in Chromium; privacy_check.py set on the 6-page eval set; example/run_example.sh end to end; and the unpack line with test_all.sh. Linux, Python 3.13, 3.12, 3.11, 3.9 and 3.8.
- Result: 75 passed, 0 failed on all five versions; 465 of 465 planted faults caught and 7 of 7 clean baselines clean; browser test 15 of 15; the eval set had 0 findings; the example caught the first-try fix with 13 findings, the old policy with 15 and the first-try report with 4, and refused piped approval; the unpack line wrote every file and test_all.sh passed there.
- Not run: A live Grok Bot, Claude Code, Codex or Hermes session. Consent platforms and tag manager containers. Safari, Firefox and real phones. Pages built by JavaScript. Non-English pages. macOS or Windows. Legal review.

Copied from this item's dated test notes. What was not run stays in.

## Worth knowing

- The agent rules were checked by the checker but not loaded inside a live Grok Bot, Claude Code, Codex or Hermes session for this release. The eval fixes were written by hand to the rules. Give your agent the entrance exam in section 15 before you rely on it.
- Not legal advice. Nothing in the kit says a site or policy meets any law. The policy check compares your policy with your pages and settings, nothing more; ask a qualified person how to word what you do with data.
- The checker reads the HTML you export. Tags fired from inside a Google Tag Manager container and pages built in the browser by JavaScript are not visible to it.
- The kit comes with its own small consent.js. It does not configure or test consent platforms such as OneTrust or Cookiebot.
- consent.js was tested in Chromium only. Safari, Firefox and real phones were not tested; every report tells the owner to check the live site in a private window.
- The owner step assumes the agent cannot run approve.py at a terminal. Run it as a separate user; agent rules alone are not a hard boundary.
- All businesses and pages in the kit are made up. English only. Tested on Linux only; macOS and Windows were not tested.
- On 2026-11-01 on Linux: 75 unit tests and 465 of 465 planted faults passed on Python 3.13, 3.12, 3.11, 3.9 and 3.8; the browser test passed 15 of 15 in Chromium; the 6-page eval set was clean; the unpack line wrote every file and test_all.sh passed in that folder.

## Questions

**Which agents does it work with?** Any agent that can read files and run a script. The kit has rules for AGENTS.md and CLAUDE.md, Claude Code and Codex notes, Hermes notes and a Grok Bot standing order. Those were checked by the checker, not loaded in each agent for this release.

**Will it change my website?** No. The agent writes fixed copies into a queue folder. You approve each one at a terminal and put it on your site yourself.

**Will it make my site compliant?** No tool can promise that, and this kit will not say it. It makes trackers wait for a choice, checks the policy against what your pages load, records what was done and lists what a person still has to check.

**Will my ad and analytics tags still work?** Yes, for visitors who say yes. The fix check refuses any change to a tracker id or tracker code, and refuses removing a tracker unless you list it for removal. Tags only run after a choice.

**Can you set it up for us?** Yes. Our Install sprint sets up your tool list, consent.js, eval set and agent, or Managed Ops runs the scans, fixes and policy updates for you each month. Book a call or write to mgmt@paperchasewebb.com.

## How to buy

$29 one time at https://paperchasewebb.ai/bots/marketplace/items/consent-privacy-fix-desk-trackers-wait-for-choice-policy-checked-owner-approved/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com