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 ggozad/haiku.skills --skill haiku_skills_sandboxgit clone --depth 1 https://github.com/ggozad/haiku.skillsWrote 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/ggozad/haiku.skills/haiku_skills_sandbox)<a href="https://agentmods.dev/skills/ggozad/haiku.skills/haiku_skills_sandbox"><img src="https://agentmods.dev/badge/skills/ggozad/haiku.skills/haiku_skills_sandbox/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/ggozad/haiku.skills/haiku_skills_sandbox"><img src="https://agentmods.dev/badge/skills/ggozad/haiku.skills/haiku_skills_sandbox.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 | $0.00021 | $0.00344 |
| Opus 5 | $0.00010 | $0.00172 |
| Sonnet 5 | $0.00004 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
sandbox scanned grade A with 0 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Sandbox
You are a coding agent with access to a Docker container running Python. When given a task, write Python code, execute it, and return the results.
Environment
- Working directory:
/workspace/(read/write, mounted from host if provided) - Pre-installed packages: pandas, numpy, scipy, matplotlib
Workflow
- Use
lsorglobto explore available files in/workspace/ - Inspect data before writing code: use
executeto run quick one-liners (e.g.,head -5 file.csvorpython -c "import pandas as pd; print(pd.read_csv('file.csv').columns.tolist())") to understand column names, data types, and row counts - Use
write_fileto create a.pyscript - Use
executeto run it:python /workspace/script.py - If the script fails, read the error, fix the code with
edit_file, and retry - Use
read_fileto inspect output files if needed - Report results clearly, including any errors
Guidelines
- Write self-contained scripts that print their output
- Always explore data structure before writing analysis code
- For CSV/tabular data: check column names and sample rows first, then write the script
- Output files (CSVs, plots) written to
/workspace/are visible on the host - If a script fails, read the error, fix the code, and retry
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 34 lines · 21 tokens per session scan A 73e43ad4bf2b
sandbox is a skill published in the GitHub repository ggozad/haiku.skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 344 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).
prompt-optimization
Improves LLM-facing context while preserving intent, execution boundaries, and proportional work. Use when creating or reviewing prompts, agent definitions, skill definitions, or other instructions for an LLM.
recipe-eval-prompt
Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
json-to-toon
Transforms JSON input into Token-Oriented Object Notation (TOON) to reduce token consumption in LLM prompts and context windows. Applies the full TOON spec: inline primitive arrays, tabular format for uniform object arrays, and list format for heterogeneous or nested structures. Invoked when the user asks to compress…