verified-script-execution

verified-script-execution is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 18 tokens per session (1,052 once invoked), scanned A, original, MIT.

A fallback workflow for creating and checking files when automated code or shell tools keep failing.

In plain words
What is it for?
It helps confirm the working directory, create scripts with shell commands, and verify important files such as PDFs, documents, and reports.
Why use it?
It gives the agent a clear recovery process instead of repeatedly retrying failed commands or writing to the wrong place.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps confirm the working directory, create scripts with shell commands, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hkuds/openspace/verified-script-execution
About the project

OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.

HKUDS/OpenSpace · 7,510 stars · on GitHub

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.

Any agent
npx skills add HKUDS/OpenSpace --skill verified-script-execution
Clone the repo
git clone --depth 1 https://github.com/HKUDS/OpenSpace

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for verified-script-execution

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/verified-script-execution.svg)](https://agentmods.dev/skills/hkuds/openspace/verified-script-execution)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/verified-script-execution"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/verified-script-execution.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,052 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.01052
Opus 5 $0.00009 $0.00526
Sonnet 5 $0.00004 $0.00210
Haiku 4.5 $0.00002 $0.00105

Measured 3d ago against content hash 387a8d1637b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verified-script-execution 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.

benchmarks/gdpval/skills/verified-script-execution/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verified Script Execution Workflow

When execute_code_sandbox or shell_agent fails repeatedly, use this manual fallback pattern to reliably create and verify files through explicit shell commands.

When to Activate This Pattern

  • After 3+ consecutive failures with execute_code_sandbox
  • When shell_agent produces repeated errors without progress
  • For critical deliverables (PDFs, Word docs, reports) that must be created reliably
  • When working directory confusion causes file creation failures

Step 1: Verify Working Directory

Always confirm your current location before creating any files:

pwd
ls -la

This ensures you're writing to the correct workspace directory and reveals any existing files that might conflict.

Step 2: Create Scripts via Heredoc

Use shell heredoc syntax to create scripts with proper escaping. Choose the heredoc delimiter style based on your needs:

For literal content (no variable expansion):

cat > script_name.sh << 'EOF'
#!/bin/bash
# Your script content here
# Variables like $VAR will NOT be expanded
echo "Literal text with $symbols"
EOF

For content requiring variable expansion:

cat > script_name.sh << EOF
#!/bin/bash
OUTPUT_DIR="$PWD/output"
# Variables WILL be expanded
echo "Working in $OUTPUT_DIR"
EOF

Key escaping rules:

  • Use << 'EOF' (quoted delimiter) to prevent variable expansion and command substitution
  • Use << EOF (unquoted delimiter) when you need shell variables expanded
  • Escape single quotes inside quoted heredoc as '\''
  • For nested heredocs, use different delimiters (e.g., EOF and INNER)

Step 3: Make Executable and Run with Explicit Path

chmod +x script_name.sh
./script_name.sh

Or use the explicit full path for certainty:

bash /full/path/to/script_name.sh

Step 4: Verify Output

Always verify file creation and inspect content:

# Check file exists and see size
ls -lh expected_output.pdf
ls -lh expected_output.docx

# For PDFs, verify structure and page count
pdfinfo expected_output.pdf

# For Word docs, inspect internal structure
unzip -l expected_output.docx | head -20

Read the full file on GitHub · 158 lines

Files

What ships with it

1 file 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 · 158 lines · 18 tokens per session scan A 387a8d1637b7

Subscribe to this mod's changes

verified-script-execution is a skill published in the GitHub repository HKUDS/OpenSpace (7,510 stars, last pushed 25d ago), licensed MIT. It adds 18 tokens to every session and 1,052 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 2026-09-03.

Related

Other skills, from other repositories

material-ui-nextjs

Integrates Material UI with Next.js App and Pages routers using @mui/material-nextjs, Emotion cache providers, next/font, CSS layers with Tailwind/CSS Modules, Link component prop patterns, CSS theme variables SSR notes, and App Router useSearchParams + Suspense. Use when setting up or debugging MUI in a Next.js app.

mui/material-ui · 76 tokens

RootCauseAnalysis

Structured incident investigation using Five Whys, Fishbone, blameless Postmortem, Fault Tree, Kepner-Tregoe, and FMEA — traces failures to systemic root causes rather than blaming humans. USE WHEN root cause, RCA, 5 whys, fishbone, postmortem, incident analysis, fault tree, why does this keep failing, blameless…

danielmiessler/LifeOS · 93 tokens

Vitals

Read-only macOS performance inspection: a deterministic CLI gathers the numbers, Interpretation.md turns them into a diagnosis instead of a data dump.

danielmiessler/LifeOS · 179 tokens

benchmark-workflow

Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.

xberg-io/xberg · 47 tokens

debugging-executions

Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.

n8n-io/n8n · 48 tokens

ai-development-guide

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

shinpr/claude-code-workflows · 43 tokens