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 hyqibot/token-free-openclaw --skill exe_bundlegit clone --depth 1 https://github.com/hyqibot/token-free-openclawWrote 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/hyqibot/token-free-openclaw/exe_bundle)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.00721 |
| Opus 5.5 | $0.00026 | $0.00288 |
| Sonnet 5.5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
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 1mo 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.
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 toMyApp.exe [args]. Examples:- Start: cwd=
scripts/MyApp, command=MyApp.exe - With args: cwd=
scripts/MyApp, command=MyApp.exe --mode live --config config/app.json
- Start: cwd=
- 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"):
- In that skill's SKILL.md set description to when to trigger (e.g. user says "run trader", "open XX app").
- In the body write: working directory = that skill's
scripts/<AppName>/, entry command =AppName.exe [args], and what each argument does. - 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.
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.
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.
- 1mo ago First seen · 58 lines · 65 tokens per session scan A f1739fdd4ad9
exe_bundle is a skill published in the GitHub repository hyqibot/token-free-openclaw (134 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 721 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
tmux
Use when a CLI task needs an interactive terminal or control of a tmux session.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-resend
Add Resend (email) channel integration via Chat SDK.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
communication
Use before sending @mentions, deciding whether to reply, TASKCOMPLETED, BLOCKED, QUESTION, direct answers, loop prevention, or suppressing low-information acknowledgements.