last-job-search / tools
CLAUDE.md7 starsChanged 21 days agoMITView on GitHub
Claude Code loads this file once a chat reads, writes or edits a file under tools/ (code.claude.com/docs/en/memory, "How CLAUDE.md files load"). Running a tool does not load it, so nothing here is needed to use the app. - Before changing any file here, read MAINTAINING.md, "Developer rules", whichever repo the chat started in: the change is made in the app, on a branch, with CI green and the leak scan passed on the exact tree; a change an existing user…
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- profile.example/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- freehire-searchSkill
- linkedin-searchSkill
- appSkill
- job-application-assistantSkill
- scrapeSkill
- networkingSkill
- upskillSkill
The file
Files
The app's code
Claude Code loads this file once a chat reads, writes or edits a file under tools/
(code.claude.com/docs/en/memory, "How CLAUDE.md files load"). Running a tool does not load
it, so nothing here is needed to use the app.
- Before changing any file here, read
MAINTAINING.md, "Developer rules", whichever repo the chat started in: the change is made in the app, on a branch, with CI green and the leak scan passed on the exact tree; a change an existing user would have to act on is a profile upgrade (tools/profile_upgrades.py); a change to a part of the build that leaves something behind is a new version intools/build_versions.py. - In a person's own copy, never edit a file here. Everything under
tools/is the app's (tools/personal_paths.pyis the line), and the next sync puts it back. If that person is not the app's maintainer, never trouble them with the app's problems: do what they asked the best honest way the app allows. tools/openroles/is vendored from openroles and never edited here.- A rule that can be enforced in Python is enforced in Python, and the words a tool prints
for a person stay plain (
tests/test_a_beginner_is_told_in_plain_words.py).
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.