claude-code-hooks-daemon / tests
CLAUDE.md4 starsChanged 16 days agoMITView on GitHub
IF YOU ARE WORKING ON A PROJECT THAT HAS HOOKS DAEMON INSTALLED — YOU MUST NOT EDIT ANYTHING IN THIS FOLDER. This is the daemon's own test suite: an upstream dependency, not part of your project. Editing files here breaks your installation, is overwritten on the next daemon update, and creates conflicts that prevent future upgrades. Unless this repository IS the daemon. In self-install (dogfood) mode the daemon's tests and the project are the same checkout, so adding a regression…
In this repository14 other files it gives its agents.
- .claude/agents/CLAUDE.mdCLAUDE.md
- CLAUDE/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .claude/skills/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- acceptance-testSkill
- configureSkill
- docs-optimiseSkill
- docs-qaSkill
- hooks-daemonSkill
- issue-sdlcSkill
- modeSkill
- releaseSkill
The file
We split this CLAUDE.md 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 4
NOT EDIT ANYTHING IN THIS FOLDER.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
DO NOT EDIT - Hooks Daemon Internal Tests
IF YOU ARE WORKING ON A PROJECT THAT HAS HOOKS DAEMON INSTALLED — YOU MUST NOT EDIT ANYTHING IN THIS FOLDER.
This is the daemon's own test suite: an upstream dependency, not part of your project. Editing files here breaks your installation, is overwritten on the next daemon update, and creates conflicts that prevent future upgrades.
Unless this repository IS the daemon. In self-install (dogfood) mode the
daemon's tests and the project are the same checkout, so adding a regression
test here is the normal way to work — see
SELF_INSTALL.md. The heading above is addressed to
a CLIENT project that installed the daemon under .claude/hooks-daemon/. Same
caution as the sibling note in ../src/CLAUDE.md: check which
case you are in before treating an instruction to add a test here as wrong.
Do This Instead
- Tests for your custom handlers — project-level handlers support
co-located tests (
test_*.pynext to each handler under.claude/project-handlers/); run them with.claude/hooks-daemon/bin/hooks-daemon test-project-handlers --verbose. See Project-Level Handlers Guide. - Found a bug — do NOT fix it here. Use the
hooks-daemonskill with argsissue-report, or read the Bug Reporting Guide: it establishes there is a defect before anything is filed, then generates a body that carries no config, logs or paths from your tree. Working notes go underuntracked/scratch/— inside the working tree, so they survive a container restart, and gitignored, so they never reach review.project_containmentdenies an ordinary redirect outside the repository, but not a path passed to a script as a plain argument — a backstop, not a guarantee.
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.

