Consent and Privacy Fix Desk: agent fixes for cookie banners, trackers and privacy policies, checked against the original, owner approved
by PaperChaseWebb
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.
- Price
- $29
- Difficulty
- Intermediate
- Setup
- 1 hr
- Format
- .md file
consent-privacy-fix-desk-trackers-wait-for-choice-policy-checked-owner-approved.md · 241 KB · instant download after checkout
Want this built for you instead? We can build it for you.
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.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
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.
Time to result: The worked example in 5 minutes; your home page scanned and fixed in about an hour
How it works
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.
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.
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.
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 prompts, free to use
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.
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.
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 the file
# 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 [email protected].
Details
Version 1.0 · Updated Nov 1, 2026 · Markdown version of this page
License: Use inside your own business or on your clients' sites. Do not resell or republish the kit itself. Download terms
Related
Consent and Privacy Fix Desk: safe consent fix rules and a ten-check page scan (free sample)
From Consent and Privacy Fix Desk: the mistakes agents make when they fix cookie banners and trackers, nine rules to paste into your agent, and a read-only script that runs ten checks on one HTML page, from trackers and pixels that fire before a choice to banners with no Reject, browse-means-yes wording, pre-ticked boxes, Google consent granted by default and compliance claims.
Accessibility Fix Desk: agent fixes for common WCAG 2.2 failures, checked against the original, owner approved
Let an agent fix the accessibility failures found on almost every site: missing alt text, unnamed links and buttons, unlabeled fields, faint text, blocked zoom, hidden focus. It writes fixed copies, never the live page. A fix check compares each copy with the original and refuses deleted or hidden content, new scripts and overlays, alt text you never wrote, colors outside your palette and aria-labels that drop the visible words. A claims check stops "fully compliant" statements. You approve at your terminal and put the page live yourself.
Search Console Fix Desk: better page titles and descriptions from your Search Console data, checked, owner approved, measured
Let an agent find the pages Google shows but people skip, and draft better titles and meta descriptions without inventing claims or touching your site. A planner compares each page with your own click rates at the same positions and decides rewrite, owner, hold or skip. A checker refuses drafts with claims or numbers the page never states, keyword stuffing, ranking promises, competitor names, noindex or redirect ideas and script overlays. You approve at your terminal and make the edit, and measure compares before and after against pages you did not touch.
Support Agent from Your Docs: grounded reply drafts, owner approval and a checker
Turn your help docs into a support agent that only says what your docs say. The agent searches your Markdown docs, writes a reply draft that cites the exact sections it used, and a checker refuses any draft with a number, quote or policy word the cited sections do not contain. Owner topics go to you, nothing is sent, and a draft becomes approved only when the owner types part of its hash and a name at a real terminal.
Review Reply Desk: AI-drafted review replies, checked for privacy and offers, approved by the owner
Let an agent draft your Google and Yelp review replies without the mistakes that cost money. A checker refuses drafts that use a last name or details from your records, offer a discount for a better review, ask for a review to be changed, argue, invent numbers or promises, or repeat your last reply word for word. Health topics, allergies and legal threats go to the owner, clinics get a stricter privacy mode, and nothing is posted until the owner approves it at a real terminal.
Ask-first rules for AI agents: hard nos, approval cards and a test set
Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.
Agency Open-Loop System: meeting notes to tasks, client follow-ups and a weekly open-loop report
A Markdown operating system plus a small checker for owner-led agencies: turn every meeting into commitments with an owner, a date, a quote and a done test, draft client follow-ups as approval cards you answer by number, and get one weekly report of what is still open. Includes AGENTS.md with six owner stops, three skills, templates and loops_check.py.