Show plugin by direct name

Author: SqlRush

docs/first-second-parity-audit.md

@@ -81,6 +81,7 @@ Anthropic API 和 conversation：
 - `/config <section>` now shares the same section-alias normalization as `/config show <section>` for non-mutating direct section invocations such as `/config env`, `/config permissions`, and `/config integrations`, while preserving existing mutating forms such as `/config model <name>` and `/config output-style <name>`.
 - `/memory list` now takes the no-query local file-list path used by `/memory show`, while `/memory status` continues to report the session/relevant-memory summary.
 - `/mcp <server-name>` now takes the no-query local server-detail path used by `/mcp show <server-name>` when the name matches a configured settings or plugin MCP server, while unknown one-word subcommands still report unsupported.
+- `/plugin <plugin-name>` now takes the no-query local plugin-detail path used by `/plugin show <plugin-name>` when the name matches a local plugin manifest, while unknown one-word subcommands still report unsupported.
 - A basic `Skill` tool wrapper is now registered with the default built-in tool set. It can invoke local project prompt skills through the command registry, returns the official-style `Launching skill: ...` result plus structured command metadata, and passes expanded meta user messages through `ToolResult.NewMessages`; the conversation runner now appends those new messages to transcripts and subsequent model requests.
 - Basic slash prompt command invocation is now wired for local project prompt skills: `/skill args` is parsed before the model request, converted into official-shaped command metadata plus expanded meta prompt messages, appended to transcript parent chains, and can override the turn model from skill frontmatter.
 - Local prompt-skill slash commands and the `Skill` tool now emit `command_permissions` attachments, parse `allowed-tools` into command-scoped permission rules, and merge those rules into the engine permission decider for the current turn so authorized follow-up tool calls can pass without leaking into later turns.

internal/conversation/run.go

@@ -2849,6 +2849,11 @@ func (r Runner) formatPluginSummary(raw string) string {
 		case "enable", "disable":
 			return r.setPluginEnabledSummary(args)
 		default:
+			if len(args) == 1 {
+				if plugin, ok := findLoadedPlugin(pluginpkg.LoadPluginDirs(pluginpkg.ProjectPluginDirs(r.WorkingDirectory)), args[0]); ok {
+					return r.formatPluginShow([]string{"show", plugin.Name})
+				}
+			}
 			return "Plugin subcommand is not implemented in the Go runtime yet: " + strings.Join(args, " ")
 		}
 	}

internal/conversation/run_test.go

@@ -4196,6 +4196,44 @@ func TestRunnerPluginShowReportsLocalPluginDetails(t *testing.T) {
 			t.Fatalf("plugin show missing %q: %q", want, text)
 		}
 	}
+
+	result, err = runner.RunTurn(context.Background(), nil, messages.UserText("/plugin demo"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(client.requests) != 0 {
+		t.Fatalf("model should not be queried, requests = %#v", client.requests)
+	}
+	text = result.Messages[1].Content[0].Text
+	for _, want := range []string{
+		"Plugin demo",
+		"State: enabled",
+		"Path: " + pluginDir,
+		"Version: 1.2.3",
+		"Description: Demo plugin",
+		"Commands: 1",
+		"Skills: 1",
+		"Agents: 1",
+		"MCP servers: 1",
+		"Output styles: 1",
+		"Hooks: 1",
+		"Commands:",
+		"- /plugin:deploy",
+		"Skills:",
+		"- /demo:audit",
+		"Agents:",
+		"- demo:reviewer",
+		"MCP servers:",
+		"- plugin:docs",
+		"Output styles:",
+		"- demo:brief",
+		"Hook events:",
+		"- PreToolUse (1)",
+	} {
+		if !strings.Contains(text, want) {
+			t.Fatalf("direct plugin show missing %q: %q", want, text)
+		}
+	}
 }
 
 func TestRunnerPluginShowReportsDisabledLocalPlugin(t *testing.T) {