Trixi.jl
CLAUDE.md737 starsChanged 14 days agoMITView on GitHub
Cross-tool agent instructions live in AGENTS.md (single source of truth) and are imported below. Add only genuinely Claude-Code-specific notes here, above the import. In Claude Code, MCP tools may be deferred: a system reminder lists only their names (e.g., mcp__julia__julia_eval), and their schemas must be loaded with ToolSearch (e.g., select:mcp__julia__julia_eval,mcp__julia__julia_restart) before the first call. Deferred tools count as available for the order of preference in Persistent Julia sessions via MCP. Before running any Julia code, check the tool list and…
In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Before running any Julia code, check the tool list and the system reminders for mcp__kaimon__* and mcp__julia__* tools.
≈ “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
CLAUDE.md
Cross-tool agent instructions live in AGENTS.md (single source of truth) and
are imported below. Add only genuinely Claude-Code-specific notes here, above
the import.
Claude Code: MCP tools may be deferred
In Claude Code, MCP tools may be deferred: a system reminder lists only their
names (e.g., mcp__julia__julia_eval), and their schemas must be loaded with
ToolSearch (e.g., select:mcp__julia__julia_eval,mcp__julia__julia_restart)
before the first call. Deferred tools count as available for the order of
preference in
Persistent Julia sessions via MCP.
Before running any Julia code, check the tool list and the system reminders for
mcp__kaimon__* and mcp__julia__* tools. Use the Bash tool for Julia only if
neither is usable (e.g., the Kaimon.jl server failed to connect and no julia-mcp
tools are listed) or for steps that AGENTS.md assigns to the shell (the
run_agents setup script).
@AGENTS.md
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.

