Comparison

A · GEMINI.md · wshobson/agents B · Cursor rules · wshobson/agents

What each file covers, counted
Dimension	Only in A	Only in B	Overlap
Sections	8	2	0%
Commands	3	2	0%
Section tags	2	5	0%

What each file covers

Sections

0 shared · 8 only in A · 2 only in B

− Gemini CLI — setup guide
− Install
− restart Gemini CLI
− What you get
− Companion Memory Extension
− Gemini-specific differences
− Regenerating
− See also
+ claude-agents conventions
+ Never

Commands

0 shared · 3 only in A · 2 only in B

− make generate HARNESS=gemini
− make generate HARNESS=gemini PLUGIN=javascript-typescript
− make clean-generated HARNESS=gemini
+ make generate HARNESS=<x>
+ make generate-all

Section tags

0 shared · 2 only in A · 5 only in B

− setup
− performance
+ lint-format
+ code-style
+ security
+ do-not
+ agent-behaviour

Line diff

+16 added−46 removed7 unchanged13.2% identical

wshobson/agents · GEMINI.md

@@ −1 @@

1# Gemini CLI — setup guide

3> The canonical context file is [`AGENTS.md`](AGENTS.md) at the repo root. Gemini CLI reads it via `.gemini/settings.json` (`context.fileName`). This guide covers Gemini-specific setup only.

5## Install

7```bash

8gemini extensions install https://github.com/wshobson/agents

9cd ~/.gemini/extensions/claude-code-workflows

10make generate HARNESS=gemini

11# restart Gemini CLI

12```

14## What you get

16- **156 skills** at `skills/<plugin>__<skill>/SKILL.md` — described in `AGENTS.md`. Describe a task to activate.

17- **192 subagents** at `agents/<plugin>__<agent>.md` — invoke with `@<agent>`.

18- **102 slash commands** at `/<plugin>:<command>` — use `/help` to list.

20## Companion Memory Extension

22Pensyve is maintained upstream as a separate Gemini CLI extension with MCP-backed

23memory and context injection:

25```bash

26gemini extensions install https://github.com/major7apps/pensyve

27```

29## Gemini-specific differences

31| Capability | Claude Code | Gemini CLI |

32|---|---|---|

33| Plugin installation | `/plugin install` | `gemini extensions install <url>` |

34| Context file | reads `CLAUDE.md` (a symlink to `AGENTS.md`) | reads via `.gemini/settings.json` redirect to AGENTS.md |

35| Per-agent tool allowlist | `tools:` (always) | `tools:` (honored — remapped to Gemini-native names) |

36| Skill / agent discovery | native | native (skills/, agents/ at extension root) |

37| Model assignment | per-agent | session-level (override via `model:` frontmatter) |

38| `TodoWrite` tool | yes | no equivalent |

40## Regenerating

42```bash

43make generate HARNESS=gemini # all plugins

44make generate HARNESS=gemini PLUGIN=javascript-typescript # one plugin

45make clean-generated HARNESS=gemini # remove output

46```

48## See also

50- [`AGENTS.md`](AGENTS.md) — canonical context (cross-harness conventions)

51- [`docs/harnesses.md`](docs/harnesses.md) — full capability matrix

52- [`docs/round-trip-results.md`](docs/round-trip-results.md) — Gemini round-trip verification recipe

wshobson/agents · .cursor/rules/000-project-conventions.mdc

@@ +1 @@

1---

2description: claude-agents marketplace project conventions

3alwaysApply: true

4---

6# claude-agents conventions

8This is a multi-harness plugin marketplace. Source lives under `plugins/`; per-harness

9artifacts (`.codex/`, `.cursor-plugin/`, `.opencode/`, `commands/`) are generated.

11- Don't hand-edit anything under `.codex/`, `.cursor-plugin/`, `.opencode/`, or top-level `commands/`, `agents/`, `skills/` — regenerate via `make generate HARNESS=<x>`.

12- Python tooling: `uv` (package manager), `ruff` (lint/format), `ty` (type check). Do not use pip/mypy/black.

13- Plugin files: `plugins/<name>/{.claude-plugin/plugin.json, agents/*.md, skills/<name>/SKILL.md, commands/*.md}`. Auto-discovered.

14- Cursor reads `.claude/skills/` and `.claude/agents/` directly — no separate `.cursor/skills/` is generated.

16## Never

18- Never commit secrets or hardcode credentials.

19- Never hand-edit generated registries (`.agents/plugins/marketplace.json`, `.cursor-plugin/`) — plugin PRs register the plugin in `.claude-plugin/marketplace.json`, then run `make generate-all` (see CONTRIBUTING.md).

20- Never run destructive git operations (force-push, reset --hard, branch -D) without explicit ask.

22See `docs/authoring.md` for the portable-content style guide.

@@ −1 +1 @@

1−# Gemini CLI — setup guide

1+---

2+description: claude-agents marketplace project conventions

3+alwaysApply: true

4+---

3−> The canonical context file is [`AGENTS.md`](AGENTS.md) at the repo root. Gemini CLI reads it via `.gemini/settings.json` (`context.fileName`). This guide covers Gemini-specific setup only.

6+# claude-agents conventions

5−## Install

8+This is a multi-harness plugin marketplace. Source lives under `plugins/`; per-harness

9+artifacts (`.codex/`, `.cursor-plugin/`, `.opencode/`, `commands/`) are generated.

610

7−```bash

8−gemini extensions install https://github.com/wshobson/agents

9−cd ~/.gemini/extensions/claude-code-workflows

10−make generate HARNESS=gemini

11−# restart Gemini CLI

12−```

11+- Don't hand-edit anything under `.codex/`, `.cursor-plugin/`, `.opencode/`, or top-level `commands/`, `agents/`, `skills/` — regenerate via `make generate HARNESS=<x>`.

12+- Python tooling: `uv` (package manager), `ruff` (lint/format), `ty` (type check). Do not use pip/mypy/black.

13+- Plugin files: `plugins/<name>/{.claude-plugin/plugin.json, agents/*.md, skills/<name>/SKILL.md, commands/*.md}`. Auto-discovered.

14+- Cursor reads `.claude/skills/` and `.claude/agents/` directly — no separate `.cursor/skills/` is generated.

1315

14−## What you get

16+## Never

1517

16−- **156 skills** at `skills/<plugin>__<skill>/SKILL.md` — described in `AGENTS.md`. Describe a task to activate.

17−- **192 subagents** at `agents/<plugin>__<agent>.md` — invoke with `@<agent>`.

18−- **102 slash commands** at `/<plugin>:<command>` — use `/help` to list.

18+- Never commit secrets or hardcode credentials.

19+- Never hand-edit generated registries (`.agents/plugins/marketplace.json`, `.cursor-plugin/`) — plugin PRs register the plugin in `.claude-plugin/marketplace.json`, then run `make generate-all` (see CONTRIBUTING.md).

20+- Never run destructive git operations (force-push, reset --hard, branch -D) without explicit ask.

1921

20−## Companion Memory Extension

21−

22−Pensyve is maintained upstream as a separate Gemini CLI extension with MCP-backed

23−memory and context injection:

24−

25−```bash

26−gemini extensions install https://github.com/major7apps/pensyve

27−```

28−

29−## Gemini-specific differences

30−

31−| Capability | Claude Code | Gemini CLI |

32−|---|---|---|

33−| Plugin installation | `/plugin install` | `gemini extensions install <url>` |

34−| Context file | reads `CLAUDE.md` (a symlink to `AGENTS.md`) | reads via `.gemini/settings.json` redirect to AGENTS.md |

35−| Per-agent tool allowlist | `tools:` (always) | `tools:` (honored — remapped to Gemini-native names) |

36−| Skill / agent discovery | native | native (skills/, agents/ at extension root) |

37−| Model assignment | per-agent | session-level (override via `model:` frontmatter) |

38−| `TodoWrite` tool | yes | no equivalent |

39−

40−## Regenerating

41−

42−```bash

43−make generate HARNESS=gemini # all plugins

44−make generate HARNESS=gemini PLUGIN=javascript-typescript # one plugin

45−make clean-generated HARNESS=gemini # remove output

46−```

47−

48−## See also

49−

50−- [`AGENTS.md`](AGENTS.md) — canonical context (cross-harness conventions)

51−- [`docs/harnesses.md`](docs/harnesses.md) — full capability matrix

52−- [`docs/round-trip-results.md`](docs/round-trip-results.md) — Gemini round-trip verification recipe

22+See `docs/authoring.md` for the portable-content style guide.

5323