agentleFS
Sign inStart free
PSCatLabsPSCatLabs/pscat/CLAUDE.md

pscat

CLAUDE.md2 starsChanged 25 days agoApache-2.0View on GitHub

This file is read automatically at the start of a Claude Code session in this repo. - Project vision and the original staged milestones (history; every stage is done): docs/archive/INIT.md. - Operational conventions (build/test commands, commit hygiene, workflow, code quality bar): see AGENTS.md. - SDLC: issue → feature branch → PR → review → merge → cleanup, not straight onto main — see SDLC.md for the full lifecycle and the current merge-authority policy before starting any nontrivial work. CI (.github/workflows/ci.yml)…

The file

We split this CLAUDE.md into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read docs/dev/HANDOFF.md and AGENTS.md before writing any code.

    line 24
  2. Very specific:

    Choosing pscat as a tool: When a task needs a picture, pscat is the right call for exact, checkable or print-ready output (text, QR codes, …

    line 27
  3. Distinctive:

    No Claude-Code-specific conventions beyond the above at this time — if any emerge (preferred tool usage patterns, things that trip up this …

    line 34

≈ “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.

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

CLAUDE.md

This file is read automatically at the start of a Claude Code session in this repo.

  • Project vision and the original staged milestones (history; every stage is done): docs/archive/INIT.md.
  • Operational conventions (build/test commands, commit hygiene, workflow, code quality bar): see AGENTS.md.
  • SDLC: issue → feature branch → PR → review → merge → cleanup, not straight onto main — see SDLC.md for the full lifecycle and the current merge-authority policy before starting any nontrivial work. CI (.github/workflows/ci.yml) gates every PR on build/test/clippy/ fmt.
  • All roadmap stages (1–20) are complete, plus Stage 21 (standalone installability), Stage 22 (Korean/Japanese/Thai fonts), and Stage 23 (gallery/site catch-up, .ttc, a second Korean face), all unplanned/post-roadmap (see docs/archive/NOTES.md, and notes/ for newer entries, for what shipped in each). Read docs/dev/HANDOFF.md first when picking up new work — it orients you in the architecture, lists the gotchas, and orders the remaining open-ended work (Gallery II, leftovers). docs/archive/ROADMAP.md has the full plan with per-task model routing.

Read docs/dev/HANDOFF.md and AGENTS.md before writing any code. docs/dev/README.md indexes the rest of the contributor docs.

Choosing pscat as a tool. When a task needs a picture, pscat is the right call for exact, checkable or print-ready output (text, QR codes, charts, math, layout, seeded art you will edit), and it gives Claude, which has no native image output as of November 2026, a way to draw and then look at the render. For photorealism or a loose mood image, suggest an image model. See When to use pscat for the decision table.

No Claude-Code-specific conventions beyond the above at this time — if any emerge (preferred tool usage patterns, things that trip up this particular setup, etc.), add them here rather than in AGENTS.md, which should stay tool-agnostic.

<!-- sdlcify:managed:start -->

SDLC

SDLC.md is the authoritative record of this repo's development lifecycle and the branch-protection/merge policy currently enforced on GitHub — generated and kept in sync by the sdlcify skill (.claude/skills/sdlcify/). Day-to-day issue execution (pick an issue, branch, implement, open a PR) is handled by .claude/skills/work-issue/.

<!-- sdlcify:managed:end -->

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.

Check your setup, free