agentleFS
tamdogoodtamdogood/parler-protocol/CLAUDE.md

parler-protocol

CLAUDE.md15 starsChanged 4 months agoApache-2.0View on GitHub

Guidance for Claude Code in this repository. Start with AGENTS.md — it is the shared onboarding map (what Parler Protocol is, the crate/architecture layout, build/test commands, and the docs/ index). This file only adds the Claude-specific rules on top. - Never run cargo fmt. This repo is hand-formatted and has no rustfmt gate; a repo-wide format reflows every file. Match surrounding style by hand. - make ci is the gate. It mirrors the cloud pipeline exactly. Run it until green…

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:

    Capture lessons: Read tasks/lessons.md at session start.

    line 40

≈ “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

CLAUDE.md

Guidance for Claude Code in this repository. Start with AGENTS.md — it is the shared onboarding map (what Parler Protocol is, the crate/architecture layout, build/test commands, and the docs/ index). This file only adds the Claude-specific rules on top.

The rules that bite

  • Never run cargo fmt. This repo is hand-formatted and has no rustfmt gate; a repo-wide format reflows every file. Match surrounding style by hand.
  • make ci is the gate. It mirrors the cloud pipeline exactly. Run it until green before calling a task done. clippy -D warnings is hard.
  • Respect the protocol contract. A change to parler-protocol ripples into parler-hub, parler-connector, and parler-cli (and the hub's REST API). Update and test all of them, not just one crate.
  • Don't weaken the security model (self-signed cards, seed never leaves device, private-by- default, join-secret for public-URL private hubs). See the security section in AGENTS.md.
  • Docs track code — no drift. Any change to user-facing behavior (CLI commands/flags, MCP tools, wire protocol, setup/config, REST API, security model) is not done until the docs match. Grep the affected surface across README.md, AGENTS.md, and docs/ for the changed name/flag/behavior, update every hit in the same PR, and leave no instruction describing the old behavior. If nothing user-facing changed, say so; otherwise treat the doc update as part of the task, not a follow-up.
  • Visible conversations have a provider contract. MCP connectivity and native visible wake are different support levels. Changes under crates/parler-cli/src/conversation* must follow docs/visible-host-adapters.md, preserve the shared parity/bounds, and update the README, troubleshooting guide, and website support matrices together.

How to work here

  • Follow the contract. docs/engineering-guidelines.md governs every change — the code-standards skill walks it step by step. Review diffs with the parler-review skill or the code-reviewer agent (.claude/agents/code-reviewer.md); both execute docs/code-review-guidelines.md.
  • Plan first for any non-trivial task (3+ steps); write the plan to tasks/todo.md. If it goes sideways, stop and re-plan rather than pushing through.
  • Use subagents for research, exploration, and parallel analysis to keep this context clean — one focused task per subagent.
  • Verify before done. Prove it works (tests, logs, real run). Would a staff engineer approve it?
  • Capture lessons. Read tasks/lessons.md at session start; append the pattern after any correction from the user so the same mistake doesn't repeat.

Simplicity first · find root causes, no temporary fixes · touch only what's necessary.

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.