Two files, one repository
wshobson/agents ships 3 formats across 5 indexed files. The question worth asking is whether the second one says anything the first does not.
| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 8 | 3 | 0% |
| Commands | 0 | 3 | 0 | 0% |
| Section tags | 0 | 2 | 2 | 0% |
What each file covers
Sections
0 shared · 8 only in A · 3 only in B- − Gemini CLI — setup guide
- − Install
- − restart Gemini CLI
- − What you get
- − Companion Memory Extension
- − Gemini-specific differences
- − Regenerating
- − See also
- + Authoring portable plugin content
- + Frontmatter
- + Body
Commands
0 shared · 3 only in A · 0 only in B- − make generate HARNESS=gemini
- − make generate HARNESS=gemini PLUGIN=javascript-typescript
- − make clean-generated HARNESS=gemini
Section tags
0 shared · 2 only in A · 2 only in B- − setup
- − performance
- + code-style
- + security
Line diff
wshobson/agents · GEMINI.md
@@ −1 @@
1# Gemini CLI — setup guide
2
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.
4
5## Install
6
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```
13
14## What you get
15
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.
19
20## Companion Memory Extension
21
22Pensyve is maintained upstream as a separate Gemini CLI extension with MCP-backed
23memory and context injection:
24
25```bash
26gemini 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
43make generate HARNESS=gemini # all plugins
44make generate HARNESS=gemini PLUGIN=javascript-typescript # one plugin
45make 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
53
wshobson/agents · .cursor/rules/020-agent-skill-authoring.mdc
@@ +1 @@
1---
2description: Authoring agent, skill, and command markdown for cross-harness portability
3globs: ["plugins/*/agents/*.md", "plugins/*/skills/*/SKILL.md", "plugins/*/commands/*.md"]
4---
5
6# Authoring portable plugin content
7
8This content ships to Claude Code, Codex CLI, Cursor, OpenCode, and Gemini CLI. The adapter
9framework handles per-harness mechanics, but content choices affect portability.
10
11## Frontmatter
12
13- Agents: `name`, `description` (with "Use when…" trigger), `model: opus|sonnet|haiku|inherit`, optional `tools:`, optional `color:`.
14- Skills: `name`, `description`. Other Anthropic SKILL.md fields are optional and respected only on Claude Code.
15- Commands: `description`, `argument-hint`.
16
17## Body
18
19- Use action verbs, not tool-name vocabulary: prefer *"open the file"* over *"use the Read tool"*. The adapter rewrites a conservative set, but the unrewritten cases bleed through.
20- Cap skill body at ~8 KB. Push longer reference material into `skills/<name>/references/` files. Codex will hard-truncate at 8 KB anyway.
21- Don't name agents `default`, `worker`, or `explorer` — they collide with Codex built-ins.
22- Don't reference `TodoWrite`, the `Task` spawn tool, or hooks as load-bearing — they don't exist in Codex or Cursor.
23
24See `docs/authoring.md` for the full guide.
25
@@ −1 +1 @@
1−# Gemini CLI — setup guide
1+---
2+description: Authoring agent, skill, and command markdown for cross-harness portability
3+globs: ["plugins/*/agents/*.md", "plugins/*/skills/*/SKILL.md", "plugins/*/commands/*.md"]
4+---
25
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+# Authoring portable plugin content
47
5−## Install
8+This content ships to Claude Code, Codex CLI, Cursor, OpenCode, and Gemini CLI. The adapter
9+framework handles per-harness mechanics, but content choices affect portability.
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+## Frontmatter
1312
14−## What you get
13+- Agents: `name`, `description` (with "Use when…" trigger), `model: opus|sonnet|haiku|inherit`, optional `tools:`, optional `color:`.
14+- Skills: `name`, `description`. Other Anthropic SKILL.md fields are optional and respected only on Claude Code.
15+- Commands: `description`, `argument-hint`.
1516
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.
17+## Body
1918
20−## Companion Memory Extension
19+- Use action verbs, not tool-name vocabulary: prefer *"open the file"* over *"use the Read tool"*. The adapter rewrites a conservative set, but the unrewritten cases bleed through.
20+- Cap skill body at ~8 KB. Push longer reference material into `skills/<name>/references/` files. Codex will hard-truncate at 8 KB anyway.
21+- Don't name agents `default`, `worker`, or `explorer` — they collide with Codex built-ins.
22+- Don't reference `TodoWrite`, the `Task` spawn tool, or hooks as load-bearing — they don't exist in Codex or Cursor.
2123
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
24+See `docs/authoring.md` for the full guide.
5325
