You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+30-12Lines changed: 30 additions & 12 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -46,7 +46,9 @@ This isn't a vibe coding tool, it's true agentic engineering, but without the ad
46
46
47
47
### Prerequisites
48
48
49
-
**Claude Subscription:** Solo developers should choose [Max 5x](https://claude.com/pricing) for moderate usage or [Max 20x](https://claude.com/pricing) for heavy usage. Teams should use [Team Premium](https://claude.com/pricing) (6.25x usage per member, SSO, admin tools, billing management). Companies with stricter compliance or procurement requirements should use [Enterprise](https://claude.com/pricing).
49
+
**Claude Code:** Pilot Shell installs on top of Claude Code — install it first [via npm](https://www.npmjs.com/package/@anthropic-ai/claude-code) or the [native installer](https://docs.anthropic.com/en/docs/claude-code/setup).
50
+
51
+
**Claude Subscription:** Solo developers should choose [Max 5x](https://claude.com/pricing) for moderate usage or [Max 20x](https://claude.com/pricing) for heavy usage. Teams should use [Team Premium](https://claude.com/pricing) (6.25x usage per member, SSO, admin tools, billing management). Companies with stricter compliance or procurement requirements should use [Enterprise](https://claude.com/pricing) (API based pricing applies per usage).
50
52
51
53
**Terminal:**[cmux](https://www.cmux.dev/) is the best terminal for Pilot Shell on macOS — built on the Ghostty rendering engine with native split panes, workspace tabs, and Claude Code notification hooks. On Linux, [Ghostty](https://ghostty.org/download) is the recommended terminal. Both are free and open source.
52
54
@@ -71,7 +73,7 @@ After installation, `cd` into any project and run `pilot` or `ccp` to start Pilo
71
73
8-step installer with progress tracking, rollback on failure, and idempotent re-runs:
|`/sync`| Explores your codebase, discovers conventions, builds a search index, updates project rules. Run once initially, then anytime your project changes. |
159
161
|`/learn`| Captures non-obvious discoveries as reusable skills. Triggers automatically or on demand. |
160
-
| Teams | Share rules, skills, commands, and agents across your team via the Console dashboard (Team plan). |
162
+
| Teams | Share rules, skills, commands, and agents across your team via the Console dashboard (Team plan). |
161
163
162
164
### Extensibility
163
165
@@ -190,6 +192,22 @@ A local web dashboard with 7 views and real-time notifications when Claude needs
190
192
191
193
</details>
192
194
195
+
### Team Asset Sharing
196
+
197
+
Share rules, skills, commands, and agents across your team from a central, private Git repository:
|**Planning**| Opus | Exploring your codebase, designing architecture, and writing the spec requires deep reasoning. A good plan is the foundation of everything. |
275
-
|**Plan Verification**| Sonnet | The plan-reviewer sub-agent validates completeness and challenges assumptions. Conditional: skipped for simple plans (≤3 tasks, clear scope). |
276
-
|**Implementation**| Sonnet | With a solid plan, writing code is straightforward. Sonnet is fast, cost-effective, and produces high-quality code when guided by a clear spec. |
|**Planning**| Opus | Exploring your codebase, designing architecture, and writing the spec requires deep reasoning. A good plan is the foundation of everything. |
293
+
|**Plan Verification**| Sonnet | The plan-reviewer sub-agent validates completeness and challenges assumptions. Conditional: skipped for simple plans (≤3 tasks, clear scope). |
294
+
|**Implementation**| Sonnet | With a solid plan, writing code is straightforward. Sonnet is fast, cost-effective, and produces high-quality code when guided by a clear spec. |
277
295
|**Code Verification**| Sonnet | The unified spec-reviewer agent handles deep code review (compliance + quality + goal). The orchestrator runs mechanical checks and applies fixes. |
278
296
279
297
Choose between Sonnet 4.6 and Opus 4.6 for the main session, each command, and sub-agents. A global "Extended Context (1M)" toggle enables the 1M token context window across all models simultaneously. **Note:** 1M context models require a Max (20x) or Enterprise subscription — not available to all users.
0 commit comments