agentleFS
silencelensilencelen/huginn/CLAUDE.md

huginn

CLAUDE.md1 starsChanged 29 days agoMITView on GitHub

Claude Code on a server you own, reached from a terminal client (bash, PowerShell, Termux), huginn core (Go), a Compose desktop app and an Android app. Start with docs/dev/README.md for the repo map and docs/dev/architecture.md for how the pieces fit. - Daemon: cd server/appd && node --test test/*.test.js (no dependencies; floors in scripts/test-floors.env). - Clients: scripts/test-client.sh (needs pwsh for the PowerShell half). - Core: cd core && go vet ./... && go test ./...; end to end: bash core/test/e2e.sh. -…

  • Reads credentials

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
  1. Very specific:

    No real addresses, host names, accounts, keys or tokens in code, tests or docs: use 192.0.2.x, example.net, alex-style placeholders.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Huginn

Claude Code on a server you own, reached from a terminal client (bash, PowerShell, Termux), huginn core (Go), a Compose desktop app and an Android app. Start with docs/dev/README.md for the repo map and docs/dev/architecture.md for how the pieces fit.

Build and test gates

  • Daemon: cd server/appd && node --test test/*.test.js (no dependencies; floors in scripts/test-floors.env).
  • Clients: scripts/test-client.sh (needs pwsh for the PowerShell half).
  • Core: cd core && go vet ./... && go test ./...; end to end: bash core/test/e2e.sh.
  • Kotlin: cd mobile && ./gradlew :core:jvmTest :core:testDebugUnitTest :ui:jvmTest :app:testDebugUnitTest :app-desktop:test. Needs the Android SDK and mobile/app/google-services.json (copy the .example).

Rules

  • client/huginn.sh and client/huginn.ps1 are a pair and print 7-bit ASCII only. Help text is generated from client/help-table.txt (node scripts/gen-help.js). After changing a client file, refresh core/internal/clientkit/files/*.txt or the drift test fails.
  • No real addresses, host names, accounts, keys or tokens in code, tests or docs: use 192.0.2.x, example.net, alex-style placeholders.
  • A new test must fail on the old code.
  • Kotlin goes in the lowest module that can hold it (:core → :ui → the app shells); see docs/dev/kotlin-clients.md.

Brand and UI

The visual identity is decided; do not improvise colours, type or state words.

  • assets/brand/BRAND.md: the rules (mark, tile, terminal art, tokens, type, motion, surfaces, voice).
  • assets/brand/design-card.html: the one-page reference, generated by python3 assets/brand/design-card.py from the token, state and mark files; regenerate it after changing any of them.
  • State language in code: mobile/ui/.../theme/StateColors.kt is the one place a state maps to a colour or a word (working · needs you · waiting · shell · ok · error · info). Needs-you is the lit accent, never colorScheme.error.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.