Skip to content
Agentmart
Submit a tool

cursor-kit

Apply Enzo Bossmann's Cursor Kit workflow in Codex for project setup, token-efficient exploration, memory continuity, verification, simplification, and safe…

Skill by Bossmann007

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bossmann007-cursor-kit

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Apply Enzo Bossmann's Cursor Kit workflow in Codex for project setup, token-efficient exploration, memory continuity, verification, simplification, and safe shipping. Use when the user asks to use, load, configure, or apply cursor-kit, token-engine, ai-memory, or the Bossmann agent stack.

Use cases: productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/cursor-kit

What's inside

Skill name
cursor-kit
Description
Apply Enzo Bossmann's Cursor Kit workflow in Codex for project setup, token-efficient exploration, memory continuity, verification, simplification, and safe shipping. Use when the user asks to use, load, configure, or apply cursor-kit, token-engine, ai-memory, or the Bossmann agent stack.
License
MIT
Instructions
36 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Cursor Kit for Codex

Use the compatible part of this repository as the default operating layer for Codex projects.

## Stack

- `token-engine` MCP: compress large tool output and context; preserve errors, paths, commands, and exact values.
- `codebase-memory` MCP: explore code structure with graph/search tools before broad reads.
- `ai-memory` MCP: long-horizon wiki and handoff context only; `AGENTS.md`, `PROJECT.md`, and `.cursor/state` remain authoritative.
- Kit skills: `setup-project`, `setup-ai-memory`, `setup-pucpr`, `verification-planning`, `simplify`, and `blindspot-pass`.

## Working rules

1. Use the smallest working change. Check whether the work is needed, reuse existing code, prefer the standard library and native features, then add the minimum code required.
2. For non-trivial work, establish an evidence path before editing: target files, validation command, and expected result.
3. After behavior is proven, run a simplify pass; before shipping, run a blind-spot pass for edge cases, silent failures, security, and accessibility.
4. When exploring a codebase, prefer `codebase-memory` search/graph/snippet/trace tools. Read a whole file only when it is the task-focus file, small, or needed after targeted exploration.
5. Compress tool output over roughly 500 tokens with `token-engine` before retaining it in context. Never drop negation, errors, paths, commands, or numbers.
6. Keep session continuity in this order: `AGENTS.md`, `PROJECT.md` decisions, `.cursor/state/checkpoint.json`, `.cursor/state/failures.jsonl`, then ai-memory handoff context.
7. Never write secrets to memory, project docs, checkpoints, skill output, commits, or ai-memory.
8. Explain non-trivial choices using a named principle or evidence from a run, test, log, or screenshot. Do not claim success without verification.
9. In Portuguese conversations, answer in Portuguese; keep code and identifiers in English unless the target project is Portuguese-first.

## Cursor-only components

Cursor `.mdc` rules and `~/.cursor/hooks.json` remain active in Cursor. Codex does not execute those files as native hooks, so apply the equivalent rules above in this skill and the global `AGENTS.md` compatibility section.

## References

- `docs/00-overview.md`
- `docs/01-installation.md`
- `docs/02-playbook-onboarding.md`
- `docs/ARCHITECTURE.md`
- `docs/MEMORY.md`

From Bossmann007/cursor-kit, MIT.

More from Bossmann007/cursor-kit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 18, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Bossmann007

Cite this page

cursor-kit skill. Agent Mart. https://agentmart.dev/skills/bossmann007-cursor-kit (last updated 2026-10-24)