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.
npx skills add vibeeval/vibecosystem --skill agent-context-isolationgit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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.
[](https://agentmods.dev/skills/vibeeval/vibecosystem/agent-context-isolation)<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/agent-context-isolation"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/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.
<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/agent-context-isolation"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/agent-context-isolation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00008 | $0.00627 |
| Opus 5.5 | $0.00003 | $0.00251 |
| Sonnet 5.5 | $0.00002 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
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 1mo 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 This is a copy
100% identical to agent-context-isolation — 162 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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:
- 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)
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.
- 1mo ago First seen · 82 lines · 8 tokens per session scan B c48d6344bc44
agent-context-isolation is a skill published in the GitHub repository vibeeval/vibecosystem (538 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 627 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 100% identical to agent-context-isolation, differing in 162 lines, and is treated as a copy.
Other skills, from other repositories
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
outlook_calendar
View, create, update, and delete events in the user's Outlook Calendar.
granola
Search and read Granola meeting notes and transcripts through Granola's OAuth-backed MCP server.
notifications
Send notifications through the unified notification router.
resume-builder
Build resume and LinkedIn profile through guided interview.