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 gni/agents-container --skill ac-isolationgit clone --depth 1 https://github.com/gni/agents-containerWrote 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/gni/agents-container/ac-isolation)<a href="https://agentmods.dev/skills/gni/agents-container/ac-isolation"><img src="https://agentmods.dev/badge/skills/gni/agents-container/ac-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/gni/agents-container/ac-isolation"><img src="https://agentmods.dev/badge/skills/gni/agents-container/ac-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 | $0.00026 | $0.00167 |
| Opus 5.5 | $0.00010 | $0.00067 |
| Sonnet 5.5 | $0.00005 | $0.00033 |
| Haiku 4.5 | $0.00003 | $0.00017 |
Grade C, and why
ac-isolation scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh What it actually says
Agent Isolation & Setup
Workspace
Root directory: /workspace
Python Virtual Environment
# Create
python3 -m venv /workspace/venv
# Activate
source /workspace/venv/bin/activate
# Install a package
pip install <package>
# Deactivate
deactivate
Rust Installation
# Install via rustup
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
# Activate in current shell
source "$HOME/.cargo/env"
# Verify
rustc --version && cargo --version
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.
- 2mo ago First seen · 40 lines · 26 tokens per session scan C ae4b332d0e23
ac-isolation is a skill published in the GitHub repository gni/agents-container (19 stars, last pushed 20d ago), licensed Apache-2.0. It adds 26 tokens to every session and 167 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
ac-isolation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ac-isolationgni/agents-container | Skill | 19 | 20d ago | Apache-2.0 | C | 26 | Claude Code, Codex |
| showagent-session-handoffaytzey/showagent | Skill | 63 | yesterday | MIT | A | 50 | Claude Code, Codex |
| wtfp-create-outlineakougkas/wtf-p | Skill | 20 | 4d ago | MIT | A | 19 | Claude Code |
| wtfp-resume-writingakougkas/wtf-p | Skill | 20 | 4d ago | MIT | A | 22 | Claude Code |
| wtfp-create-posterakougkas/wtf-p | Skill | 20 | 4d ago | MIT | A | 22 | Claude Code |
| wtfp-create-slidesakougkas/wtf-p | Skill | 20 | 4d ago | MIT | A | 23 | Claude Code |
| wtfp-execute-outlineakougkas/wtf-p | Skill | 20 | 4d ago | MIT | A | 18 | Claude Code |