RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Diff/wshobson-agents-gemini ↔ wshobson-agents-agents

Comparison

A · GEMINI.md · wshobson/agentsB · AGENTS.md · wshobson/agents
What each file covers, counted
DimensionSharedOnly in AOnly in BOverlap
Sections0880%
Commands1298%
Section tags0260%

What each file covers

Sections

0 shared · 8 only in A · 8 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 — multi-harness agentic plugin marketplace
  • + Map
  • + Working in this repo
  • + Quality gates (run these before pushing)
  • + Regenerating per-harness artifacts
  • + Skills (cross-harness)
  • + Subagents (cross-harness)
  • + Why this file is short

Commands

1 shared · 2 only in A · 9 only in B
  • − make generate HARNESS=gemini PLUGIN=javascript-typescript
  • − make clean-generated HARNESS=gemini
  • + make validate STRICT=1
  • + make garden
  • + make test
  • + make smoke-test
  • + make generate HARNESS=codex
  • + make generate HARNESS=cursor
  • + make generate HARNESS=opencode
  • + make generate-all
  • + task
  •   make generate HARNESS=gemini

Section tags

0 shared · 2 only in A · 6 only in B
  • − setup
  • − performance
  • + test
  • + lint-format
  • + code-style
  • + security
  • + do-not
  • + agent-behaviour

Line diff

+59 added−35 removed18 unchanged23.4% identical
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 · AGENTS.md
@@ +1 @@
1# claude-agents — multi-harness agentic plugin marketplace
2 
3Production-ready agentic-workflow building blocks: **94 plugins** (90 local + 4 external), **203 agents**, **175 skills**, **109 commands**. Native source-of-truth for Claude Code; also consumed by OpenAI Codex CLI, Cursor, OpenCode, and Gemini CLI from a single Markdown source.
4 
5This file is the canonical context file. Codex / Cursor / OpenCode read it directly. Claude Code reads it via `CLAUDE.md`, a symlink to this file. Gemini CLI reads it via `gemini-extension.json` (`contextFileName`) / `.gemini/settings.json`.
6 
7> **Read this file like a table of contents.** Detail lives in `docs/`. Authoring conventions live in `docs/authoring.md`. Per-harness setup and capability deltas live in [`docs/harnesses.md`](docs/harnesses.md). Gemini-specific setup is in `GEMINI.md` (also auto-loaded by Gemini CLI). This file should never grow beyond ~150 lines (per OpenAI's [harness-engineering](https://openai.com/index/harness-engineering/) practice).
 
 
 
 
 
8 
9## Map
10 
11- **[ARCHITECTURE.md](ARCHITECTURE.md)** — top-level architectural overview (adapter framework, source-of-truth invariant, capability matrix summary)
12- **[docs/architecture.md](docs/architecture.md)** — detailed design principles
13- **[docs/plugins.md](docs/plugins.md)** — full plugin catalog (94 plugins by category)
14- **[docs/agents.md](docs/agents.md)** — agent reference (203 agents, model tiers)
15- **[docs/agent-skills.md](docs/agent-skills.md)** — skill reference (progressive disclosure model)
16- **[docs/usage.md](docs/usage.md)** — commands, workflows, examples
17- **[docs/authoring.md](docs/authoring.md)** — portable-content style guide (read before adding plugins)
18- **[docs/harnesses.md](docs/harnesses.md)** — per-harness capability matrix
19- **[docs/plugin-eval.md](docs/plugin-eval.md)** — three-layer quality evaluation framework
20- **[docs/round-trip-results.md](docs/round-trip-results.md)** — real-CLI verification recipes
21- **[CONTRIBUTING.md](CONTRIBUTING.md)** — how to contribute
22 
23## Working in this repo
24 
25- Python tooling: **uv** (package manager), **ruff** (lint/format), **ty** (type check). Do not use pip / mypy / black.
26- Plugins live under `plugins/<name>/` with auto-discovery — see `docs/authoring.md` for frontmatter shapes.
27- Plugin names: lowercase, hyphen-separated. Never use `__` (it's the adapter namespace separator).
28- Never commit secrets. Never run destructive git (force-push, `reset --hard`, branch -D) without explicit ask.
29 
30## Quality gates (run these before pushing)
31 
32```bash
33make validate STRICT=1 # structural validation across all harness outputs
34make garden # drift detection (dead links, stale artifacts, oversize skills)
35make test # full pytest suite (plugin-eval + tools/tests/)
36make smoke-test # real-CLI subprocess tests against generated artifacts
37```
38 
39CI (`.github/workflows/validate.yml`) runs all four on every PR plus installs OpenCode + Gemini CLI for live verification.
40 
41## Regenerating per-harness artifacts
 
 
 
 
 
 
 
42 
 
 
43```bash
44make generate HARNESS=codex # .codex/skills, .codex/agents, .codex/plugins/<p>/, .agents/plugins/marketplace.json
45make generate HARNESS=cursor # .cursor-plugin/{marketplace,plugin}.json, .cursor/rules/
46make generate HARNESS=opencode # .opencode/{skills,agents,commands,plugins}/, opencode.json
47make generate HARNESS=gemini # skills/, agents/, commands/ at extension root
48make generate-all # all four
49```
50 
51Generated artifacts are **committed** so each harness installs natively from a clone / GitHub URL (native-install commands in [`docs/harnesses.md`](docs/harnesses.md)). Run `make generate-all` before committing source changes — CI fails on drift. Source-of-truth lives only under `plugins/`; never hand-edit generated files.
52 
53## Skills (cross-harness)
54 
55175 skills under `plugins/*/skills/<n>/SKILL.md` — discoverable by every harness:
56 
57- **Claude Code**: auto-discovery via Anthropic's SKILL.md spec
58- **Codex CLI**: mirrored to `.codex/skills/<plugin>__<skill>/` (8 KB body cap; detail in `references/details.md`)
59- **OpenCode**: mirrored to `.opencode/skills/<plugin>-<skill>/` using hyphenated names for global install
60- **Cursor**: reads `.claude/skills/` directly (no re-emit)
61- **Gemini CLI**: native skills at `skills/<plugin>__<skill>/SKILL.md`
62 
63Top-level `skills/` is Gemini output; do not use it for OpenCode installs.
64 
65## Subagents (cross-harness)
66 
67203 subagents under `plugins/*/agents/<name>.md`. Per-harness transpilation:
68 
69- **Codex**: `.codex/agents/<plugin>__<agent>.toml` (drop `tools:`, map model alias to the GPT-5.x family, infer `sandbox_mode`)
70- **OpenCode**: `.opencode/agents/<plugin>__<agent>.md` with `mode: subagent` + `permission:` block (locked agents — those with source `tools: []` — get deny-everything except base `skill`/`task`)
71- **Gemini**: `agents/<plugin>__<agent>.md` (April 2026 subagent spec)
72- **Cursor**: reads `.claude/agents/` directly
73 
74## Why this file is short
75 
76Per OpenAI's harness-engineering practice: this file is a **map**, not an encyclopedia. Procedural detail lives in skills (loaded on demand by agents). Reference material lives in `docs/` (loaded when an agent navigates). A single bloated AGENTS.md crowds out the task, rots quickly, and is hard to verify mechanically. Keep it lean; push detail elsewhere.
77 
@@ −1 +1 @@
1−# Gemini CLI — setup guide
1+# claude-agents — multi-harness agentic plugin marketplace
22  
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.
3+Production-ready agentic-workflow building blocks: **94 plugins** (90 local + 4 external), **203 agents**, **175 skills**, **109 commands**. Native source-of-truth for Claude Code; also consumed by OpenAI Codex CLI, Cursor, OpenCode, and Gemini CLI from a single Markdown source.
44  
5−## Install
5+This file is the canonical context file. Codex / Cursor / OpenCode read it directly. Claude Code reads it via `CLAUDE.md`, a symlink to this file. Gemini CLI reads it via `gemini-extension.json` (`contextFileName`) / `.gemini/settings.json`.
66  
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−```
7+> **Read this file like a table of contents.** Detail lives in `docs/`. Authoring conventions live in `docs/authoring.md`. Per-harness setup and capability deltas live in [`docs/harnesses.md`](docs/harnesses.md). Gemini-specific setup is in `GEMINI.md` (also auto-loaded by Gemini CLI). This file should never grow beyond ~150 lines (per OpenAI's [harness-engineering](https://openai.com/index/harness-engineering/) practice).
138  
14−## What you get
9+## Map
1510  
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.
11+- **[ARCHITECTURE.md](ARCHITECTURE.md)** — top-level architectural overview (adapter framework, source-of-truth invariant, capability matrix summary)
12+- **[docs/architecture.md](docs/architecture.md)** — detailed design principles
13+- **[docs/plugins.md](docs/plugins.md)** — full plugin catalog (94 plugins by category)
14+- **[docs/agents.md](docs/agents.md)** — agent reference (203 agents, model tiers)
15+- **[docs/agent-skills.md](docs/agent-skills.md)** — skill reference (progressive disclosure model)
16+- **[docs/usage.md](docs/usage.md)** — commands, workflows, examples
17+- **[docs/authoring.md](docs/authoring.md)** — portable-content style guide (read before adding plugins)
18+- **[docs/harnesses.md](docs/harnesses.md)** — per-harness capability matrix
19+- **[docs/plugin-eval.md](docs/plugin-eval.md)** — three-layer quality evaluation framework
20+- **[docs/round-trip-results.md](docs/round-trip-results.md)** — real-CLI verification recipes
21+- **[CONTRIBUTING.md](CONTRIBUTING.md)** — how to contribute
1922  
20−## Companion Memory Extension
23+## Working in this repo
2124  
22−Pensyve is maintained upstream as a separate Gemini CLI extension with MCP-backed
23−memory and context injection:
25+- Python tooling: **uv** (package manager), **ruff** (lint/format), **ty** (type check). Do not use pip / mypy / black.
26+- Plugins live under `plugins/<name>/` with auto-discovery — see `docs/authoring.md` for frontmatter shapes.
27+- Plugin names: lowercase, hyphen-separated. Never use `__` (it's the adapter namespace separator).
28+- Never commit secrets. Never run destructive git (force-push, `reset --hard`, branch -D) without explicit ask.
2429  
30+## Quality gates (run these before pushing)
31+ 
2532 ```bash
26−gemini extensions install https://github.com/major7apps/pensyve
33+make validate STRICT=1 # structural validation across all harness outputs
34+make garden # drift detection (dead links, stale artifacts, oversize skills)
35+make test # full pytest suite (plugin-eval + tools/tests/)
36+make smoke-test # real-CLI subprocess tests against generated artifacts
2737 ```
2838  
29−## Gemini-specific differences
39+CI (`.github/workflows/validate.yml`) runs all four on every PR plus installs OpenCode + Gemini CLI for live verification.
3040  
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 |
41+## Regenerating per-harness artifacts
3942  
40−## Regenerating
41− 
4243 ```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
44+make generate HARNESS=codex # .codex/skills, .codex/agents, .codex/plugins/<p>/, .agents/plugins/marketplace.json
45+make generate HARNESS=cursor # .cursor-plugin/{marketplace,plugin}.json, .cursor/rules/
46+make generate HARNESS=opencode # .opencode/{skills,agents,commands,plugins}/, opencode.json
47+make generate HARNESS=gemini # skills/, agents/, commands/ at extension root
48+make generate-all # all four
4649 ```
4750  
48−## See also
51+Generated artifacts are **committed** so each harness installs natively from a clone / GitHub URL (native-install commands in [`docs/harnesses.md`](docs/harnesses.md)). Run `make generate-all` before committing source changes — CI fails on drift. Source-of-truth lives only under `plugins/`; never hand-edit generated files.
4952  
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+## Skills (cross-harness)
54+ 
55+175 skills under `plugins/*/skills/<n>/SKILL.md` — discoverable by every harness:
56+ 
57+- **Claude Code**: auto-discovery via Anthropic's SKILL.md spec
58+- **Codex CLI**: mirrored to `.codex/skills/<plugin>__<skill>/` (8 KB body cap; detail in `references/details.md`)
59+- **OpenCode**: mirrored to `.opencode/skills/<plugin>-<skill>/` using hyphenated names for global install
60+- **Cursor**: reads `.claude/skills/` directly (no re-emit)
61+- **Gemini CLI**: native skills at `skills/<plugin>__<skill>/SKILL.md`
62+ 
63+Top-level `skills/` is Gemini output; do not use it for OpenCode installs.
64+ 
65+## Subagents (cross-harness)
66+ 
67+203 subagents under `plugins/*/agents/<name>.md`. Per-harness transpilation:
68+ 
69+- **Codex**: `.codex/agents/<plugin>__<agent>.toml` (drop `tools:`, map model alias to the GPT-5.x family, infer `sandbox_mode`)
70+- **OpenCode**: `.opencode/agents/<plugin>__<agent>.md` with `mode: subagent` + `permission:` block (locked agents — those with source `tools: []` — get deny-everything except base `skill`/`task`)
71+- **Gemini**: `agents/<plugin>__<agent>.md` (April 2026 subagent spec)
72+- **Cursor**: reads `.claude/agents/` directly
73+ 
74+## Why this file is short
75+ 
76+Per OpenAI's harness-engineering practice: this file is a **map**, not an encyclopedia. Procedural detail lives in skills (loaded on demand by agents). Reference material lives in `docs/` (loaded when an agent navigates). A single bloated AGENTS.md crowds out the task, rots quickly, and is hard to verify mechanically. Keep it lean; push detail elsewhere.
5377  
RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack