exe_bundle

exe_bundle is a skill for Claude Code, Codex from hyqibot/token-free-openclaw. It costs 65 tokens per session (721 once invoked), scanned A, original, Apache-2.0.

Instructions for running a packaged Windows desktop application made of an executable file, supporting libraries, and resource files. It explains where to place the files, which working directory to use, and how to start the executable.

In plain words
What is it for?
Use it when adding or running a bundled Windows desktop app as a skill, including apps that need configuration, data, templates, or command-line arguments.
Why use it?
It prevents the application from failing to find its DLLs, configuration, or other files. Keeping related files together also makes the start command predictable.

Skill for Claude CodeCodex

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

Good fit Use it when adding or running a bundled Windows desktop app as a skill, including apps that need configuration, data, templates, or command-line arguments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hyqibot/token-free-openclaw/exe_bundle
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 hyqibot/token-free-openclaw --skill exe_bundle
Clone the repo
git clone --depth 1 https://github.com/hyqibot/token-free-openclaw

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 exe_bundle

README.md
[![agentmods](https://agentmods.dev/badge/skills/hyqibot/token-free-openclaw/exe_bundle/github.svg)](https://agentmods.dev/skills/hyqibot/token-free-openclaw/exe_bundle)
Your own site
<a href="https://agentmods.dev/skills/hyqibot/token-free-openclaw/exe_bundle"><img src="https://agentmods.dev/badge/skills/hyqibot/token-free-openclaw/exe_bundle/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.

agentmods 80×15 button for exe_bundle

Your own site · 80×15
<a href="https://agentmods.dev/skills/hyqibot/token-free-openclaw/exe_bundle"><img src="https://agentmods.dev/badge/skills/hyqibot/token-free-openclaw/exe_bundle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 721 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00065 $0.00721
Opus 5 $0.00032 $0.00360
Sonnet 5 $0.00013 $0.00144
Haiku 4.5 $0.00006 $0.00072

Measured 10d ago against content hash f1739fdd4ad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

exe_bundle 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 10d 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.

copaw/agents/skills/exe_bundle/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Packaged exe + libraries/dll + resource files

This skill defines how to add a packaged desktop app (exe + dlls/libs + config/data) as a CoPaw skill and how the agent should run it.

Placement

  • Put exe, dependency libraries (dlls), and resource files in a single subdirectory under this skill's scripts/ folder, e.g.:
    • scripts/MyApp/
      Containing: MyApp.exe, dlls/libs, and config or data (e.g. config/, data/, *.json).
  • Working directory (cwd) must be that subdirectory (e.g. scripts/MyApp) so the exe finds dlls and relative-path resources.

Entry command

  • Windows: In the shell, set cwd to scripts/MyApp (or your actual subdirectory) and command to MyApp.exe [args]. Examples:
    • Start: cwd=scripts/MyApp, command=MyApp.exe
    • With args: cwd=scripts/MyApp, command=MyApp.exe --mode live --config config/app.json
  • Keep paths relative to that directory; do not use absolute paths in the command—rely on cwd.

Resource files

  • If the app needs config, data, templates, place them in the same directory or a subdirectory (e.g. scripts/MyApp/config/, scripts/MyApp/data/). No need to mention absolute paths in SKILL.md.
  • Do not put secrets in SKILL.md; note "read from memory or env" or let the app read from a config file in the same directory.

When adding a concrete app as a skill

For a new skill for a specific app (e.g. "my trader exe"):

  1. In that skill's SKILL.md set description to when to trigger (e.g. user says "run trader", "open XX app").
  2. In the body write: working directory = that skill's scripts/<AppName>/, entry command = AppName.exe [args], and what each argument does.
  3. Put exe, dlls, and resources under that skill's scripts/<AppName>/.

Example (SKILL.md snippet)

---
name: my_trader
description: "When the user wants to start the trading app, run backtest, or check positions; this skill uses the packaged trader.exe."
---

## Entry (working directory = scripts/trader)

- Start: cwd=`scripts/trader`, command=`trader.exe`
- Backtest: cwd=`scripts/trader`, command=`trader.exe --backtest --config config/backtest.json`
- Positions: cwd=`scripts/trader`, command=`trader.exe --query positions`

Exe, dlls, and resources are under `scripts/trader/`; no Python or system install required.

Read the full file on GitHub · 58 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. 10d ago First seen · 58 lines · 65 tokens per session scan A f1739fdd4ad9

Subscribe to this mod's changes

exe_bundle is a skill published in the GitHub repository hyqibot/token-free-openclaw (122 stars, last pushed 18d ago), licensed Apache-2.0. It adds 65 tokens to every session and 721 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 2026-08-30.