New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Context Isolation

by parcadei in parcadei/Continuous-Claude-v3

“Agent Context Isolation”

— description from SKILL.md by parcadei
MITAuto-check passedAgent Workflows

Install Agent Context Isolation

skills CLI
$ npx skills add parcadei/Continuous-Claude-v3 --skill agent-context-isolation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install parcadei/Continuous-Claude-v3 agent-context-isolation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/agent-context-isolation .claude/skills/agent-context-isolation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-context-isolation
GitHub stars
3.9k
Used in
2 other repos
Token cost
~679 tokens
SKILL.md length
181 words
Files
1
Skills in repo
141
Repo updated
First seen
Licence
MIT

At a glance

  • Works in 5 steps: Use Background Agents with File-Based… → Never Use TaskOutput to Retrieve Results → Monitor Agent Progress via System… → …
  • SKILL.md covers Rules, Why This Matters and Source
  • Calls bun

About this skill

Agent Context Isolation is a skill in parcadei/Continuous-Claude-v3 (3.9k stars). Its SKILL.md is about 679 tokens, and copies of it appear in 2 other owners' repositories. Licence: MIT.

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Use Background Agents with File-Based Coordination
  2. Never Use TaskOutput to Retrieve Results
  3. Monitor Agent Progress via System Reminders
  4. Verify with Tests, Not Output
  5. File-Based Agent Pipeline Pattern

What it can do on your machine

Read from SKILL.md and the folder at commit d07ff4b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bun

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Context Isolation loads about 679 tokens when it runs. Until then it costs about 12 tokens; SKILL.md has 181 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~12
When it runs · the whole SKILL.md, loaded when a task matches
~679

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from parcadei/Continuous-Claude-v3 at commit d07ff4b, republished under its MIT licence (© parcadei). 181 words, ~679 tokens.

Download SKILL.mdSave it as .claude/skills/agent-context-isolation/SKILL.md (or your agent's skills folder).
name
agent-context-isolation
description
Agent Context Isolation
user-invocable
false

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 tests

TaskOutput 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>.output

Stuck agent detection:

  1. Progress reminders stop arriving
  2. Task output file size stops growing
  3. Expected output file not created after reasonable time
4. Verify with Tests, Not Output

After agent work:

  1. Run the test suite directly: bun test
  2. Report pass/fail counts
  3. 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

© parcadei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/agent-context-isolation of parcadei/Continuous-Claude-v3.

Open the folder on GitHubat commit d07ff4b

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in parcadei/Continuous-Claude-v3, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Agent Context Isolation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Context Isolation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Context Isolation this skillparcadei/Continuous-Claude-v33.9k2 repos~679Automated safety check: PassMIT
ccc Semantic Code Searchcocoindex-io/cocoindex-code2.7k—~938Automated safety check: PassApache-2.0
Context Engineeringabashev/vfs-s31069 repos~2.6kAutomated safety check: NotesApache-2.0
Repomix Codebase Packeryamadashy/repomix29k—~1.3kAutomated safety check: NotesMIT
Codebase Handbook BuilderRuhan-Wang/Harness_Handbook332—~2.2kAutomated safety check: PassApache-2.0
CodemapJordanCoin/codemap704—~1.8kAutomated safety check: PassMIT

Similar skills

  • ccc Semantic Code Search

    cocoindex-io/cocoindex-code

    Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.

    2.7k GitHub stars~938 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Context Engineering

    abashev/vfs-s3

    Optimizes agent context setup. An agent skill from abashev/vfs-s3.

    106 GitHub starsUsed in 9 repos~2.6k tokens
    Agent WorkflowsAuto-check: notes

  • Repomix Codebase Packer

    yamadashy/repomix

    Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.

    29k GitHub stars~1.3k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check: notes

  • Codebase Handbook Builder

    Ruhan-Wang/Harness_Handbook

    Generates, refreshes, validates and uses a compact handbook that maps where a change touches in a repository, using the active Codex session and no external LLM API.

    332 GitHub stars~2.2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Codemap

    JordanCoin/codemap

    Gives an agent a quick map of a codebase's structure, dependencies, changes and handoffs, and tunes per-project config so the output stays code-first.

    704 GitHub stars~1.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Repomix Context Skill

    sopaco/deepwiki-rs

    A skill your agent uses when an agent needs source code from the local repomix index under .terrain/agent/repomix.md (not committed; regenerate via Terrain scan).

    3.1k GitHub stars~671 tokensUpdated 24 days ago
    Agent WorkflowsAuto-check passed

More from parcadei/Continuous-Claude-v3

All 141 skills in this repo

  • Tldr Deep

    parcadei/Continuous-Claude-v3

    Full 5-layer analysis of a specific function. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 2 repos~677 tokens
    Auto-check passed

  • Compound Learnings

    parcadei/Continuous-Claude-v3

    Transform session learnings into permanent capabilities (skills, rules, agents).

    3.9k GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check: notes

  • Gradient Methods

    parcadei/Continuous-Claude-v3

    Problem-solving strategies for gradient methods in optimization

    3.9k GitHub starsUsed in 3 repos~1k tokens
    Auto-check: notes

  • Debug Hooks

    parcadei/Continuous-Claude-v3

    Systematic hook debugging workflow. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~863 tokens
    Auto-check: notes

  • Math

    parcadei/Continuous-Claude-v3

    Unified math capabilities - computation, solving, and explanation.

    3.9k GitHub starsUsed in 3 repos~1.6k tokens
    Auto-check: notes

  • Math Model Selector

    parcadei/Continuous-Claude-v3

    Routes problems to appropriate mathematical frameworks using expert heuristics

    3.9k GitHub starsUsed in 3 repos~841 tokens
    Auto-check passed

Categories

Questions about Agent Context Isolation

How do I install Agent Context Isolation in Claude Code?

Run `npx skills add parcadei/Continuous-Claude-v3 --skill agent-context-isolation -a claude-code`. Or copy the skill folder (.claude/skills/agent-context-isolation in parcadei/Continuous-Claude-v3) into .claude/skills/agent-context-isolation in your project. Claude Code loads it when a task matches its description.

How do I install Agent Context Isolation in Codex?

Run `npx skills add parcadei/Continuous-Claude-v3 --skill agent-context-isolation -a codex`. Or copy the skill folder (.claude/skills/agent-context-isolation in parcadei/Continuous-Claude-v3) into .agents/skills/agent-context-isolation in your project. Codex loads it when a task matches its description.

Can I use Agent Context Isolation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add parcadei/Continuous-Claude-v3 --skill agent-context-isolation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-context-isolation, .gemini/skills/agent-context-isolation, .github/skills/agent-context-isolation and .opencode/skills/agent-context-isolation in your project.

What does Agent Context Isolation need to run?

Going by SKILL.md and its folder, Agent Context Isolation needs the command-line tools its instructions call (bun).

Does Agent Context Isolation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Context Isolation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Context Isolation use?

Agent Context Isolation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Context Isolation use?

About 679 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Context Isolation?

Skills that share tags, products or a category with Agent Context Isolation: ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.7k stars), Context Engineering (abashev/vfs-s3, 106 stars), Repomix Codebase Packer (yamadashy/repomix, 29k stars) and Codebase Handbook Builder (Ruhan-Wang/Harness_Handbook, 332 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Context Isolation?

parcadei (a GitHub user) maintains it in parcadei/Continuous-Claude-v3, which has 3,940 GitHub stars. The repository holds 141 skills in this directory. The repository was last updated on January 26, 2026.

Source: parcadei/Continuous-Claude-v3 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.