How I Triage Release Notes Before Claude Code Turns Them Into a Product Video

A developer wrote a small standard-library Python script that triages a Keep a Changelog-formatted CHANGELOG.md before an AI agent turns it into a product video, sorting each entry into keep, cut, or human-review verdicts. The script flags internal work like dependency bumps for cutting, vague or jargon-heavy entries for rewriting, and security items for human review, aiming to catch coverage and overconfidence errors in a table rather than in a finished render. The developer notes the sorting itself is the boring part, and the rows the script refuses to decide are the interesting ones.

Ask an agent to make a video from CHANGELOG.md and it will often treat every line as content, including the dependency bump. Nothing looks wrong until the render, where the React upgrade has six seconds of screen time. I would rather argue about a cut list than about a finished video. So I wrote a small script that sorts a changelog into keep, cut and "a human should look" before the agent sees it. The sorting turned out to be the boring part. The rows the script refuses to decide are the interesting ones. A changelog is written for the team that shipped the release. It records what happened, in the order a maintainer thinks about it, and nothing in the file says which entries a customer cares about. That leaves an agent two ways to go wrong. The first is coverage: it can treat every line as content. The second is confidence: when a line is thin, a model tends to fill the gap with a stronger headline than the line supports. A fix for one crash turns into "crashes are gone". Both mistakes are cheap to catch in a table and expensive to catch in a render. It reads a changelog in the Keep a Changelog https://keepachangelog.com/en/1.1.0/ layout, takes the newest dated release, and prints a verdict for every entry. It uses only the standard library. bash /usr/bin/env python3 """Draft a keep/cut table for the newest dated release in a CHANGELOG.md.""" import argparse import re import sys from pathlib import Path RELEASE = re.compile r"^ \s+\ ? ?P<ver ^\ \s + \ ?\s ?:-\s ?P<date \d{4}-\d{2}-\d{2} ? ?P<tail . $" INTERNAL = re.compile r"\b bump|upgrade sd ?|dependenc\w+|deps?|refactor\w |lint\w |chore|typo|tests?|ci|rename sd ? \b", re.I JARGON = re.compile r"\b race condition|deadlock|mutex|queue|worker|thread|pool|cache|index|orm|migration script \b", re.I def newest release lines : """Return version, date, {group: entries } for the first dated, non-yanked release.""" release, group, found = None, None, for line in lines: m = RELEASE.match line if m: release, group = m, None if m "date" and "yanked" not in m "tail" .lower : found.append m "ver" , m "date" , {} continue if line.startswith " " : group = line 4: .strip elif re.match r"^ - \s+", line and release and found and release "date" \ and "yanked" not in release "tail" .lower and group: found -1 2 .setdefault group, .append re.sub r"^ - \s+", "", line .strip return found 0 if found else None def triage group, entry : if group == "Security": return "ASK", "a person decides if this goes on screen" if INTERNAL.search entry : return "CUT", "reads as internal work" if len entry.split < 4: return "REWRITE", "too vague to turn into a headline" if JARGON.search entry : return "REWRITE", "names a component customers never see" if group in "Deprecated", "Removed" : return "SCENE", "customers lose something, say it plainly" return "SCENE", "" def main : ap = argparse.ArgumentParser ap.add argument "path" ap.add argument "--title", type=int, default=3, help="title card seconds" ap.add argument "--per", type=int, default=6, help="seconds per scene" ap.add argument "--cap", type=int, default=40, help="runtime cap in seconds" ap.add argument "--strict", action="store true", help="exit 1 if ASK or REWRITE rows remain" args = ap.parse args rel = newest release Path args.path .read text .splitlines if not rel: sys.exit "No dated, non-yanked release found." ver, date, groups = rel print f"Release {ver} {date} \n" print "| Group | Entry | Verdict | Why |" print "|---|---|---|---|" scenes, open rows = 0, 0 for group, entries in groups.items : for e in entries: verdict, why = triage group, e scenes += verdict == "SCENE" open rows += verdict in "ASK", "REWRITE" print f"| {group} | {e} | {verdict} | {why} |" runtime = args.title + scenes args.per flag = " <- over the cap" if runtime args.cap else "" print f"\n{scenes} scenes, about {runtime}s of {args.cap}s{flag}" if args.strict and open rows: sys.exit 1 if name == " main ": main The rules are deliberately dumb: Unreleased , because those lines haven't shipped. It also ignores any release marked YANKED , because that release was pulled. Here is the file I tested with. The app, Fieldnote, is made up so there is no real customer data in it. Unreleased Added - Shared folders behind a feature flag . 2.8.0 - 2026-10-14 Added - Offline mode for iOS. - Tag filters in search. Changed - Upgrade React to 19.1. - Search results open faster on large libraries. Removed - Dropped the legacy Markdown importer. Fixed - Fix race condition in sync queue. - Fix crash when opening notes over 10,000 characters. - Misc fixes. Security - Sanitize HTML in the note preview. 2.7.1 - 2026-09-30 YANKED Fixed - Fix login redirect. And what python changelog triage.py CHANGELOG.md printed: | Group | Entry | Verdict | Why | |---|---|---|---| | Added | Offline mode for iOS. | SCENE | | | Added | Tag filters in search. | SCENE | | | Changed | Upgrade React to 19.1. | CUT | reads as internal work | | Changed | Search results open faster on large libraries. | SCENE | | | Removed | Dropped the legacy Markdown importer. | SCENE | customers lose something, say it plainly | | Fixed | Fix race condition in sync queue. | REWRITE | names a component customers never see | | Fixed | Fix crash when opening notes over 10,000 characters. | SCENE | | | Fixed | Misc fixes. | REWRITE | too vague to turn into a headline | | Security | Sanitize HTML in the note preview. | ASK | a person decides if this goes on screen | The footer reads 5 scenes, about 33s of 40s . The shared-folders flag and the yanked 2.7.1 never appear, which is the point. Two rows deserve a second look. "Search results open faster on large libraries" got a SCENE verdict, and the script is right to let it through. But a speed claim invites a number, and the note doesn't contain one. If an agent writes "twice as fast" on that scene, it made the number up. I would catch that in the brief, not in the render. The "Misc fixes" row is the other. No script can fix it. Someone who knows what shipped has to write the real line, and that is the whole argument for doing this triage before the agent runs. Setup is the boring part and the docs cover it better than I would. In the CoAnimator app, Settings, General, Command line and agent skill has an install button for each, and the CLI docs https://coanimator.com/docs/cli cover the command. Claude Code comes from Anthropic's setup guide https://code.claude.com/docs/en/setup . If you want background on what the agent can do inside a project, this post https://coanimator.com/blog/can-claude-code-make-videos covers it. Then I would send the dated section, the table, and a brief like this: Here is a triage table for Fieldnote 2.8.0 and the dated changelog section it came from. Treat the table as a proposal. For each row, confirm or overrule the verdict and give one sentence of reasoning. For REWRITE rows, propose a customer-facing line and quote the source words it came from. Do not state any number, speed or percentage that is not in the notes. Build nothing until I reply. The last two instructions do most of the work. "Quote the source words" forces every headline to point at its entry, and "build nothing until I reply" turns the first answer into something you can correct for the price of one sentence. Each SCENE row also needs a screenshot or recording to attach, or the scene will be text on a background. Once the build is approved, the render step is a single coa render <project . For a quick look at the title card, --start 0 --end 6 renders only the first six seconds. The script can't check the rest, so I go through these: git describe --tags --abbrev=0 prints the latest tag in one second. --strict makes the script exit 1 while any ASK or REWRITE row is unresolved. I tested the exit code locally, and I haven't wired it into a release pipeline yet. The step itself is two lines: - name: Changelog triage run: python changelog triage.py CHANGELOG.md --strict Any Security entry fails strict mode on purpose, so a person has to look at it. Once someone has, run that release without --strict . The table prints to the job log, so whoever reviews the failed run sees exactly which rows need a person. It matches words, not meaning, and it will be wrong in both directions: That is why the script proposes and the agent and I decide. It also can't tell whether a change is visible to a customer, because it only sees the words. One privacy point. The script runs locally, but whatever you paste into an agent can leave your machine for its provider. CoAnimator's quickstart https://coanimator.com/docs/quickstart says the same about files and frames sent to an AI provider. Delete embargoed rows from the table before pasting, and crop customer data out of screenshots. Does it work with changelogs that aren't in Keep a Changelog format? It needs version - date headings and groups. GitHub's generated release notes have neither, so the parser would need a small change. Does the script replace reading the notes? No. It's a first draft of the cut list so the conversation with the agent starts from something concrete. Do I need CoAnimator for this? No. The table works with any agent or video workflow. I use CoAnimator for the render step. Regex is a fallback. The better signal is the person who wrote the change. A customer-facing label on the pull request, or a one-line release-note field in the PR template, would let the table come from labels and leave the regex to catch whatever nobody labeled. Then the triage happens at merge time, when the author still remembers why the change matters. Try the script on your last release and see which rows you disagree with. Those are the decisions your changelog never recorded. If you want to turn the approved rows into a video, the CoAnimator desktop app https://coanimator.com/download is where I'd render them or you can use your existing video workflow.