code-execution-helper

A guide for using code execution to process many files or results in batches, filter for relevant items, and combine findings into summaries.

In plain words
What is it for?
Use it to scan multiple files, find selected issues such as critical vulnerabilities, validate large result sets, aggregate data, and reduce unnecessary context.
Why use it?
It helps agents handle large amounts of data more efficiently instead of loading every file or result into the conversation.

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/davidmatousek/tachi/code-execution-helper
Any agent
npx skills add davidmatousek/tachi --skill code-execution-helper
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,305 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 $0.00076 $0.03305
Opus 5 $0.00038 $0.01653
Sonnet 5 $0.00015 $0.00661
Haiku 4.5 $0.00008 $0.00331

Measured 3d ago against content hash 31e68a85f993, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-execution-helper 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/code-execution-helper/SKILL.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Execution Helper

This skill provides guidance for using code execution capabilities efficiently in Claude Code workflow agents. Code execution enables agents to perform parallel batch processing, conditional filtering, and data aggregation while dramatically reducing token consumption.

About Code Execution

Code execution allows agents to run TypeScript code in a sandboxed Deno runtime, enabling operations that would otherwise require loading massive amounts of data into context. By processing data in the execution environment and returning only filtered or aggregated results, agents can achieve 30-95% token reduction for high-value use cases.

Key Benefits

  1. Parallel batch processing - Scan 10+ files simultaneously instead of sequentially
  2. Conditional filtering - Return only relevant data (e.g., CRITICAL vulnerabilities only)
  3. Data aggregation - Summarize patterns across multiple sources
  4. Token efficiency - Process large datasets without context window limits
  5. Quota awareness - Check API limits before execution to prevent failures

When to Use Code Execution

Use code execution when tasks meet these criteria:

  • Multiple operations: More than 5 files, API calls, or validation checks
  • Large datasets: Results exceed 10,000 tokens if loaded into context
  • Conditional logic: Need to filter, aggregate, or transform data before returning
  • Parallel processing: Operations can run simultaneously for faster execution
  • Token efficiency: Reducing context usage is important for the workflow

When NOT to Use Code Execution

Avoid code execution for:

  • Single operations: One file scan, one API call, simple queries
  • Small datasets: Results under 2,000 tokens
  • Direct responses: User needs raw data without filtering
  • Simple queries: Questions answerable with existing tools
  • Debugging code execution itself: Use direct tools to avoid recursion

Decision Criteria

To determine whether to use code execution, apply these thresholds:

Read the full file on GitHub · 410 lines

Files

What ships with it

6 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. 3d ago First seen · 410 lines · 76 tokens per session scan A 31e68a85f993

Subscribe to this mod's changes

code-execution-helper is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 20d ago), licensed Apache-2.0. It adds 76 tokens to every session and 3,305 once invoked, about $0.0004 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 2026-08-30.