agent-context-isolation
- Repo stars 3,783
- Author updated Live
- Author repo Continuous-Claude-v3
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @parcadei · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: agent-context-isolation
description: Agent Context Isolation Prevent agent output from polluting the main context window. Task(subage…
category: ai
runtime: no special runtime
---
# agent-context-isolation output preview
## PART A: Task fit
- Use case: Agent Context Isolation Prevent agent output from polluting the main context window. Task(subagenttype="...", runin_background=true, prompt="... Output to: /path/to/file.md") runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Rules / 1. Use Background Agents with File-Based Coordination / 2. Never Use TaskOutput to Retrieve Results” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Agent Context Isolation Prevent agent output from polluting the main context window. Task(subagenttype="...", runin_background=true, prompt="... Output to: /path/to/file.md") runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Rules / 1. Use Background Agents with File-Based Coordination / 2. Never Use TaskOutput to Retrieve Results” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source mentions slash commands such as `/path`, `/tmp`; use them first when your agent supports command triggers.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “Rules / 1. Use Background Agents with File-Based Coordination / 2. Never Use TaskOutput to Retrieve Results”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: agent-context-isolation
description: Agent Context Isolation Prevent agent output from polluting the main context window. Task(subage…
category: ai
source: parcadei/Continuous-Claude-v3
---
# agent-context-isolation
## When to use
- Agent Context Isolation Prevent agent output from polluting the main context window. Task(subagenttype="...", runin_ba…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Rules / 1. Use Background Agents with File-Based Coordination / 2. Never Use TaskOutput to Retrieve Results” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "agent-context-isolation" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Rules / 1. Use Background Agents with File-Based Coordination / 2. Never Use TaskOutput to Retrieve Results
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Agent Context Isolation
Prevent agent output from polluting the main context window.
Rules
1. Use Background Agents with File-Based Coordination
# RIGHT - background agent writes to file, main reads file
Task(subagent_type="...", run_in_background=true, prompt="... Output to: /path/to/file.md")
# WRONG - foreground agent dumps full transcript into main context
Task(subagent_type="...", run_in_background=false)Background agents with run_in_background=true isolate their context. Have them write results to files in .claude/cache/agents/<agent-type>/.
2. Never Use TaskOutput to Retrieve Results
# WRONG - dumps entire transcript (70k+ tokens) into context
TaskOutput(task_id="<id>")
TaskOutput(task_id="<id>", block=true)
# RIGHT - check expected output files
Bash("ls -la .claude/cache/agents/<agent-type>/")
Bash("bun test") # verify with testsTaskOutput returns the full agent transcript. Always use file-based coordination instead.
3. Monitor Agent Progress via System Reminders
# System reminders come automatically:
# "Agent a42a16e progress: 6 new tools used, 88914 new tokens"
# To detect completion:
# - Watch for progress reminders to stop arriving
# - Poll for expected output files: find .claude/cache/agents -name "*.md" -mmin -5
# - Check task output file size growth: wc -c /tmp/claude/.../tasks/<id>.outputStuck agent detection:
- Progress reminders stop arriving
- Task output file size stops growing
- Expected output file not created after reasonable time
4. Verify with Tests, Not Output
After agent work:
- Run the test suite directly:
bun test - Report pass/fail counts
- Only investigate failures if tests fail
5. File-Based Agent Pipeline Pattern
Research agent → .claude/cache/agents/oracle/output.md
↓
Plan agent → .claude/cache/agents/plan-agent/output.md (reads research)
↓
Validate agent → .claude/cache/agents/validate-agent/output.md (reads plan)
↓
Implement agent → src/module.ts (reads validated plan)Each agent reads the previous agent's file output, not TaskOutput.
Why This Matters
Agent context isolation preserves the main conversation's context budget. Reading agent outputs via TaskOutput floods context, causing:
- Mid-conversation compaction
- Lost context about user's original request
- Repeated explanations needed
Source
- Session where TaskOutput flooded 70k+ tokens into main context
- Session 2026-01-01: Successfully used background agents with file-based coordination for SDK Phase 3
Decide Fit First
Design Intent
How To Use It
Boundaries And Review