sandbox-algorithms

A method for running small, deterministic algorithm calculations in an EdgeOne code sandbox. It covers tasks such as number sequences, prime checks, sorting, combinations, permutations, and simple dynamic-programming examples.

In plain words
What is it for?
Use it for Fibonacci numbers, factorials, prime numbers, sorting and searching examples, combinations, permutations, and small dynamic-programming demonstrations.
Why use it?
It provides a way to compute or verify straightforward results with code rather than relying only on mental calculation.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tencentedgeone/claude-agent-starter-python/sandbox-algorithms
Any agent
npx skills add TencentEdgeOne/claude-agent-starter-python --skill sandbox-algorithms
Clone the repo
git clone --depth 1 https://github.com/TencentEdgeOne/claude-agent-starter-python

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.00593
Opus 5 $0.00033 $0.00296
Sonnet 5 $0.00013 $0.00119
Haiku 4.5 $0.00007 $0.00059

Measured 2d ago against content hash db09c3a7cfd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sandbox-algorithms 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/algorithms.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/sandbox-algorithms/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandbox Algorithms

Purpose

Execute small deterministic algorithm tasks through the EdgeOne sandbox code interpreter instead of relying only on model reasoning.

Filesystem (critical)

This skill directory exists only on the Claude Code host (the agent process). It is not mounted into the EdgeOne sandbox.

After this skill loads, do not list or search the skill base directory.

Never call files_list, files_read, files_exists, or commands on:

  • this skill's base directory
  • /tmp/user-code
  • .claude/skills
  • any other agent cwd path

Those tools operate on a separate sandbox VM and will return not found.

If you need scripts/algorithms.py, use Claude Code Read on .claude/skills/sandbox-algorithms/scripts/algorithms.py. For typical algorithm questions, skip that file and run a self-contained snippet.

When to Use

Use this skill for requests involving:

  • Fibonacci sequence calculation.
  • Factorial calculation.
  • Prime or composite number checks.
  • Prime list generation.
  • Sorting or searching examples.
  • Combination, permutation, or binomial coefficient calculation.
  • Small dynamic programming demonstrations.
  • User requests that explicitly mention sandbox execution, runCode, code_interpreter, or algorithm scripts.

Workflow

  1. Identify the algorithm task and required inputs.
  2. Write a small self-contained Python snippet. Do not probe the skill directory first.
  3. Execute the snippet with the EdgeOne sandbox code_interpreter tool.
  4. Inspect results, logs, and error.
  5. If execution fails, fix the code and run once more.
  6. Return the final answer with a short explanation and the executed result.

Tool Usage Rules

  • Use code_interpreter for actual computation whenever available.
  • Do not fake tool outputs.
  • Do not rely only on mental arithmetic for requested algorithm execution.
  • Keep code snippets deterministic and self-contained. Put the full implementation in the code argument; do not import host skill files.
  • Set a reasonable timeout, usually 5 to 15 seconds for small algorithms.
  • Avoid network access unless the user explicitly asks for it.
  • Avoid writing files unless a file is necessary for the task.

Read the full file on GitHub · 83 lines

Files

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.

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. 2d ago First seen · 83 lines · 66 tokens per session scan A db09c3a7cfd0

Subscribe to this mod's changes

sandbox-algorithms is a skill published in the GitHub repository TencentEdgeOne/claude-agent-starter-python (2 stars, last pushed 6d ago), licensed MIT. It adds 66 tokens to every session and 593 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens