legal-ai-engineering-lab
CLAUDE.md2 starsChanged 3 months agoMITView on GitHub
An import is expanded at launch and enters context in full. It organises content; it does not defer it. Do not "shrink" AGENTS.md by importing more files here — real deferral comes from skills, path-scoped rules, and documents the agent chooses to open. --> - Path-scoped rules. Some directories carry their own AGENTS.md, holding rules that apply only inside them. .claude/rules/ is generated from those files with the matching paths: frontmatter, because Claude Code reads .claude/rules/ and not a nested…
In this repository21 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- .claude/rules/agents.mdAGENTS.md
- evals/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- architecture-reviewSkill
- code-reviewSkill
- evaluation-reviewSkill
- explainSkill
- interview-reviewSkill
- learning-reviewSkill
- security-reviewSkill
- start-projectSkill
- architecture-reviewSkill
- code-reviewSkill
- evaluation-reviewSkill
- explainSkill
- interview-reviewSkill
- learning-reviewSkill
- security-reviewSkill
- start-projectSkill
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 32
If the import above was not expanded, read AGENTS.md in full before doing substantial work and apply it as though its contents appeared …
≈ “Common” is an estimate: at least 1 in 5 of the 28,029 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
Legal Engineering Lab — Claude Code
@AGENTS.md
<!--
Maintainer note. `AGENTS.md` is the canonical cross-agent contract; this file is a thin
Claude adapter and should stay that way. A symlink would also work on macOS and Linux, but
a Windows checkout without Developer Mode turns one into a text file containing the target
path, so an import is used instead. See docs/decisions/0002.
An import is expanded at launch and enters context in full. It organises content; it does
not defer it. Do not "shrink" AGENTS.md by importing more files here — real deferral comes
from skills, path-scoped rules, and documents the agent chooses to open.
-->Claude-specific
- Path-scoped rules. Some directories carry their own
AGENTS.md, holding rules that apply only inside them..claude/rules/is generated from those files with the matchingpaths:frontmatter, because Claude Code reads.claude/rules/and not a nestedAGENTS.md. Edit the nested file and runuv run python scripts/sync_agent_files.py; never edit.claude/rules/directly, as it is overwritten. Seedocs/decisions/0005. /explainis the owner's command. It is never yours to invoke.- Permissions.
.claude/settings.jsonallowlists this repository's own commands. Anything outside that list —uv add, for instance — prompts for approval. Warn the owner before it appears, so the prompt reads as the system working rather than as an error. - A pre-read guard refuses tool access to
data/real/,data/client/, anddata/private/. It covers three known locations and cannot establish that anything else is safe. The instruction inAGENTS.mdremains primary: if the owner describes a file as real or confidential, stop before reading it, wherever it sits.
If the import above was not expanded, read AGENTS.md in full before doing substantial work
and apply it as though its contents appeared here.
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.

