agentleFS
Sign inStart free
kensauruskensaurus/cursor-kenji/AGENTS.md

cursor-kenji

AGENTS.md9 starsChanged 42 days agoMITView on GitHub

This repo is the playbook pack: skills + slash commands + agents + rules. npx @kensaurus/skills --all installs Cursor, Claude Code, Codex CLI, and Gemini CLI; a bare npx stays Cursor-only. npx skills add is skills-only. Default install merges; --clean is opt-in. Descriptions cap at 320 chars. Do not submit the Official MCP Registry — we ship templates, not a server. Model story. One model, routed by effort: deep-reasoning families declare effort: high, mechanical ones effort: low, implementation inherits the…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this AGENTS.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:

    Default install merges; --clean is opt-in.

    line 9
  2. Very specific:

    Decision memory: Before proposing a change to architecture, dependencies, conventions, or distribution, read docs/adr/INDEX.md.

    line 27
  3. Distinctive:

    Do not contradict an Accepted ADR silently — surface it, cite the ADR, and ask.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
AGENTS.md

Agent notes — kenji

Architecture in one breath

This repo is the playbook pack: skills + slash commands + agents + rules. npx @kensaurus/skills --all installs Cursor, Claude Code, Codex CLI, and Gemini CLI; a bare npx stays Cursor-only. npx skills add is skills-only. Default install merges; --clean is opt-in. Descriptions cap at 320 chars. Do not submit the Official MCP Registry — we ship templates, not a server.

Model story. One model, routed by effort: deep-reasoning families declare effort: high, mechanical ones effort: low, implementation inherits the default (ADR-0006). There is no "strong planner / fast executor" split; approved plans run under approved-plan-execution.mdc (ADR-0007). Every description without disable-model-invocation: true rides Claude Code's skill listing; validate-skills measures it the way the client does and fails above LISTING_MAX_CHARS (ADR-0010), and commands are /-only while skills keep the auto-route (ADR-0008). Reasoning depth is effort, never a reasoning MCP server (ADR-0009). Model and host version facts live in the ADRs, not here.

docs/AGENTS.template.md is the constitution copied into other repos. Do not treat it as this pack's own agent notes.

Decision memory. Before proposing a change to architecture, dependencies, conventions, or distribution, read docs/adr/INDEX.md. Do not contradict an Accepted ADR silently — surface it, cite the ADR, and ask. A reversal produces a superseding ADR, by the human, on purpose. New decisions that meet the bar in the index land as an ADR in the same PR.

Support

  • Support / publisher contact: kensaurus@gmail.com (.claude-plugin marketplace email).
  • Listings and "do not submit" tables: docs/DISTRIBUTION.md.

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