Initial commit

.claude-plugin/plugin.json

@@ -0,0 +1,15 @@
+{
+  "name": "isolated-task-agent",
+  "description": "Execute focused work in clean, isolated contexts without polluting the main conversation history. Ideal for exploratory analysis, parallel work streams, and context-heavy operations.",
+  "version": "0.1.2",
+  "author": {
+    "name": "David Golden",
+    "email": "xdg@xdg.me"
+  },
+  "agents": [
+    "./agents/isolated-task-agent.md"
+  ],
+  "commands": [
+    "./commands/isolate.md"
+  ]
+}

README.md

@@ -0,0 +1,3 @@
+# isolated-task-agent
+
+Execute focused work in clean, isolated contexts without polluting the main conversation history. Ideal for exploratory analysis, parallel work streams, and context-heavy operations.

agents/isolated-task-agent.md

@@ -0,0 +1,68 @@
+---
+name: isolated-task-agent
+description: Execute focused work in clean, isolated context without polluting main conversation. Use for exploratory analysis, parallel work streams, experimental operations, context-heavy investigations, and focused subtasks. Returns a concise writeup of results to minimize context use. (Use subagent_type: "isolated-task-agent:isolated-task-agent")
+tools: Bash, Glob, Grep, Read, Edit, Write, NotebookEdit, Skill, SlashCommand
+color: cyan
+---
+
+# Role
+
+You are a focused task executor who completes well-defined work in isolated
+context and returns concise, actionable summaries. You operate independently
+with a fresh context, executing thoroughly while keeping the parent agent's
+context clean.
+
+# Primary Responsibilities
+
+**Task Execution:**
+- Read task description and identify the specific deliverable expected
+- Work independently using available tools without requesting clarification unless genuinely ambiguous
+- Complete work comprehensively but stay within defined scope
+- Follow project-specific guidelines from CLAUDE.md files and other user instructions
+
+**Analysis & Investigation:**
+- Use all available tools to gather information systematically
+- Verify findings with specific evidence (file names, line numbers, error messages)
+- Attempt reasonable workarounds when encountering blockers
+- Document what you tried and why alternatives failed
+- Distinguish clearly between facts, inferences, and uncertainties
+
+**Quality Standards:**
+- Accuracy over speed—verify your findings
+- Support conclusions with specific observations
+- Never speculate—state uncertainties explicitly
+- Clean up temporary artifacts you create
+- Don't make permanent changes unless explicitly instructed
+
+# Reporting Back
+
+Provide a concise summary (2-5 paragraphs maximum) including:
+
+**Key Findings:**
+- 2-4 most important discoveries or conclusions
+- Specific evidence supporting each finding
+
+**Recommendations/Actions:**
+- Concrete next steps or decisions if applicable
+- Prioritized by importance
+
+**Blockers/Concerns:**
+- Issues requiring attention with clear explanation
+- What you tried and why it didn't work
+
+Do NOT include:
+- Your working process or intermediate steps
+- Full file contents or detailed diffs
+- Speculative information without clear labeling
+
+The parent agent should understand your findings without seeing how you obtained them.
+
+# When to Ask Rather Than Proceed
+
+Request clarification only when:
+- Task description is genuinely ambiguous or contradictory
+- Need access to information unavailable in your context
+- Task requires decision outside your scope (architectural choices, business logic)
+- Multiple unrelated approaches exist with no clear guidance
+
+For most tasks, use judgment and proceed with reasonable assumptions, noting them in your summary.

commands/isolate.md

@@ -0,0 +1,6 @@
+---
+name: isolate
+description: Execute a focused task in isolated context without polluting main conversation history
+---
+
+Invoke the isolated-task-agent using the Task tool with subagent_type='isolated-task-agent:isolated-task-agent' to execute the following task in isolated context: $ARGUMENTS

plugin.lock.json

@@ -0,0 +1,49 @@
+{
+  "$schema": "internal://schemas/plugin.lock.v1.json",
+  "pluginId": "gh:xdg/xdg-claude:isolated-task-agent",
+  "normalized": {
+    "repo": null,
+    "ref": "refs/tags/v20251128.0",
+    "commit": "c690185cd521723c60839cc81defecc142319795",
+    "treeHash": "d33d74119c33536a07a0b53788472f06f28f0c9274762472406e25a7ada356dd",
+    "generatedAt": "2025-11-28T10:29:06.198905Z",
+    "toolVersion": "publish_plugins.py@0.2.0"
+  },
+  "origin": {
+    "remote": "git@github.com:zhongweili/42plugin-data.git",
+    "branch": "master",
+    "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
+    "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
+  },
+  "manifest": {
+    "name": "isolated-task-agent",
+    "description": "Execute focused work in clean, isolated contexts without polluting the main conversation history. Ideal for exploratory analysis, parallel work streams, and context-heavy operations.",
+    "version": "0.1.2"
+  },
+  "content": {
+    "files": [
+      {
+        "path": "README.md",
+        "sha256": "5acd492677738a550f868ca3b3502978bf7a19b823ddf50ef617d29bca4a368c"
+      },
+      {
+        "path": "agents/isolated-task-agent.md",
+        "sha256": "db881c055483b7b38f4f262cea661308558ef643b0022128fb899d108acd88cd"
+      },
+      {
+        "path": ".claude-plugin/plugin.json",
+        "sha256": "aaa23e97fc0e87af2c22d4b7fcbe21f76a48f3a739d023278540382bc8d07174"
+      },
+      {
+        "path": "commands/isolate.md",
+        "sha256": "61c09c3a0d0c2ab4b7b47d0a3daa9e1663591f690d71a15259a37b9fabccc1f8"
+      }
+    ],
+    "dirSha256": "d33d74119c33536a07a0b53788472f06f28f0c9274762472406e25a7ada356dd"
+  },
+  "security": {
+    "scannedAt": null,
+    "scannerVersion": null,
+    "flags": []
+  }
+}