agent-context-isolation

agent-context-isolation is a skill for Claude Code from parcadei/Continuous-Claude-v3. It costs 8 tokens per session (623 once invoked), scanned B, original, MIT.

A set of rules for keeping work from background coding agents out of the main conversation. Background agents are separate helpers that can work while the main agent continues.

In plain words
What is it for?
Use it when delegating exploration or implementation to background agents, saving their results in files, checking those files, and monitoring progress.
Why use it?
It prevents long agent transcripts from filling the conversation and makes results easier to inspect through files.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it when delegating exploration or implementation to background agents, saving their results in files, checking those files, and monitoring progress.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parcadei/continuous-claude-v3/agent-context-isolation
About the project

Continuous-Claude-v3 is a Claude Code development environment that preserves working context between sessions, coordinates specialized agents, and stores project knowledge through ledgers, handoffs, and analysis tools. It is for people using Claude Code on ongoing or complex software work. Its catalogue entries are the skills, agents, hooks, plugin, and setting that provide its workflows and orchestration.

parcadei/Continuous-Claude-v3 · 3,936 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add parcadei/Continuous-Claude-v3 --skill agent-context-isolation
Clone the repo
git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-context-isolation

README.md
[![agentmods](https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/agent-context-isolation/github.svg)](https://agentmods.dev/skills/parcadei/continuous-claude-v3/agent-context-isolation)
Your own site
<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/agent-context-isolation"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/agent-context-isolation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-context-isolation

Your own site · 80×15
<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/agent-context-isolation"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/agent-context-isolation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 623 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 15 Feb 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00008 $0.00623
Opus 5 $0.00004 $0.00311
Sonnet 5 $0.00002 $0.00125
Haiku 4.5 $0.00001 $0.00062

Measured 9d ago against content hash 2559aec9ef8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

agent-context-isolation scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

# - Poll for expected output files: find .claude/cache/agents -name "*.md" -mmin -5
Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/skills/agent-context-isolation/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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)

Read the full file on GitHub · 82 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 82 lines · 8 tokens per session scan B 2559aec9ef8e

Subscribe to this mod's changes

agent-context-isolation is a skill published in the GitHub repository parcadei/Continuous-Claude-v3 (3,936 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 623 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

sfl

Save For Later: checkpoint this window so a fresh session (or /nil) can resume it later. Use when the user types /sfl, "save for later", or "checkpoint this window". Writes a live per-window entry under /.claude/sfl/ (plus an optional durable note in the user's own memory system), then shows the green Saved-for-Later…

wasulajr/headsup · 121 tokens

synthesize

Deep cross-domain synthesis engine for the vault. Triggers on "synthesize X", "what do I know about X", "connect ideas about X", "cross-domain analysis of X", "map everything in the vault about X". Searches comprehensively, surfaces non-obvious patterns and tensions, then challenges the user to generate original…

tuan3w/obsidian-vault-agent · 89 tokens

init

Initialize an Obsidian vault with the agent-ready Zettelkasten system — creates directory structure, templates, CLAUDE.md, MCP config, and hooks.

tuan3w/obsidian-vault-agent · 34 tokens

kb-lint

Use to health-check an llmkb knowledge base — run llmkb lint and fix what it reports, then do the judgment-level checks code cannot: contradictions between pages, stale claims superseded by newer sources, and missing concept pages.

hogu-dev/llmkb · 54 tokens

kb-init

Use to create a new llmkb knowledge base for a project — scaffold it with llmkb init, then interview the user briefly to tailor SCHEMA.md to the project's domain and conventions.

hogu-dev/llmkb · 44 tokens

vault-graph

Use when analyzing vault structure, finding orphan notes, discovering missing connections, identifying bridge concepts, or checking vault health from a graph perspective. Triggers on "vault graph", "map vault", "find orphans", "missing links", "vault structure", "knowledge graph".

tuan3w/obsidian-vault-agent · 59 tokens