todo-extractor
Skill48 starsChanged 17 days agoMITView on GitHub
Finds TODO, FIXME, HACK and XXX comments across a source tree and groups them by tag and file. Use when the user asks for a list of open tasks in the code, wants to plan cleanup work, or needs an inventory of technical debt.
In this repository15 other files it gives its agents.
- api-endpoint-testerSkill
- changelog-generatorSkill
- commit-message-writerSkill
- csv-profilerSkill
- dockerfile-linterSkill
- env-file-auditorSkill
- json-diffSkill
- log-analyzerSkill
- meeting-notes-to-actionsSkill
- pr-description-writerSkill
- python-code-smellsSkill
- readme-doctorSkill
- secure-code-reviewSkill
- skill-authorSkill
- sql-query-reviewerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Before archiving or handing over a project.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
TODO extractor
Turns scattered comments into a planning list.
When to use
- The user asks "what is left to do in this repo?".
- Planning a cleanup sprint or a release, where known shortcuts must be reviewed.
- Before archiving or handing over a project.
How to run
python scripts/find_todos.py src/
python scripts/find_todos.py . --tags TODO,FIXMEHidden folders, node_modules, venv, dist, build and binary files are skipped.
Output
JSON with total, by_tag (counts) and items, a list of {"file", "line", "tag", "text"}
sorted by file and line. The exit code is always 0 when the path exists.
After running
- Lead with the counts per tag.
FIXMEandHACKusually matter more thanTODO. - Group items by file or folder and point out hot spots.
- Propose an order of work, and mark items that look stale (they mention past dates or removed code).
Errors
A path that does not exist exits with code 2.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.