Comment to DM Delivery: see which comments would get a reply (free sample)
by PaperChaseWebb
A read-only dry run and a sample register from Comment to DM Delivery. Paste real comments from a post and see which would get a private reply, which are opt-outs, and which near-misses would not fire. Plus the six rules worth keeping.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 5 min
- Format
- .md file
comment-to-dm-delivery-keyword-dry-run-free-sample.md · 3 KB · direct download, no signup
What you end up with
You see how your keywords would behave before you connect anything.
What you get
- dry_run.py: read-only, sends nothing
- A sample register and sample comments
- The six rules worth keeping
- One prompt for your agent
Who it is for
Anyone who wants to test a keyword before going live.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: One Python script and two text files. Tested on Linux.
Tools needed
Cost to run: Free.
Time to result: About five minutes
Sample prompts, free to use
Run python3 dry_run.py register.csv comments.txt and tell me which keywords would fire and any comment that fired by accident. Do not change the register.
The script, register and sample comments are in the file.
Free preview of the file
# Comment to DM Delivery: free dry run **See which comments would get a private reply before anything is connected.** A read-only script, a sample register and the rules from the full kit. ## What it does `dry_run.py` reads your register and a text file of comments and tags each one: REPLY with the keyword, no reply, or OPT-OUT. It matches whole words only, so "guidelines" does not fire "guide", and paused rows never fire. It sends nothing and needs no account. ## Run it 1. Save the three files below. 2. Put real comments from one of your posts into `comments.txt`, one per line. 3. `python3 dry_run.py register.csv comments.txt` Prompt for Grok Bot, Claude Code, Codex or Hermes: > Run python3 dry_run.py register.csv comments.txt and tell me which keywords would fire and any comment that fired by accident. Do not change the register. ## The rules worth keeping, even without the kit 1. Reply only to people who commented a keyword you published. 2. One private reply per comment, within 7 days of the comment (Meta's rule for posts and reels; Source: Meta Instagram Platform docs, private replies, checked Nov 1, 2026). 3. Follow-ups by a person, only after they reply, and within 24 hours of that reply (Meta's rule). 4. Approve the exact message text before it goes live. 5. STOP ends it, at once. 6. A kill switch that starts in the off position. ## The full kit adds The Cloudflare Worker on Meta's official private reply path with signature checks, one-reply claims, the 7-day window, a conservative hourly cap you set and opt-outs; a register checker with 16 checks; a weekly log review; the three-st
Test record
- Date
- Nov 1, 2026
- What was run
- tests/test_mini.py on Linux, Python 3.8, 3.9, 3.11, 3.12 and 3.13.
- Result
- 1 passed on all five versions.
- Not run
- Everything the full kit does.
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- The sample only reads and tags. The worker, register checker, log review, test protocol and agent rules are in the full kit.
- On 2026-11-01 its test passed on Linux with Python 3.8 to 3.13.
Questions
Does it connect to Instagram?
No. It reads two local files and prints tags.
What is in the full kit?
The Cloudflare Worker on Meta's private reply path, a 16-check register checker, a weekly log review, the three-stage test protocol, agent rules and 20 tests. $29.
Details
Version 1.0 · Updated Nov 1, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related

Comment to DM Delivery: keyword opt-in, one private reply, owner-approved copy
Someone comments your keyword on an Instagram post and gets one private reply with the link they asked for, on Meta's official private reply path. A small Cloudflare Worker you own checks the signature, matches whole words against a register you approve, sends once per comment within Meta's 7-day window, honors STOP at once and starts paused.

Text Message Consent Desk: safe text fixing rules and a ten-check text scan (free sample)
From Text Message Consent Desk: the mistakes agents make when they tidy a business's texts, nine rules to paste into your agent, and a read-only script that runs ten checks on one saved text, from a missing STOP line and opt-outs that ask for a log-in to link shorteners, fake Re: lines, offers inside reminders, late send times and compliance claims.