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 agentmods add skills/myunwang/llmpet/register-generated-programnpx skills add myunwang/LLMPET --skill register-generated-programgit clone --depth 1 https://github.com/myunwang/LLMPETWhat 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 | $0.00071 | $0.00495 |
| Opus 5 | $0.00036 | $0.00247 |
| Sonnet 5 | $0.00014 | $0.00099 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
register-generated-program scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Register Codex Program
Add a Codex-created shortcut to LLMPET Launcher only after proving the deliverable really runs.
Workflow
- Identify the user-facing launch path. Prefer the same command or file the user should run later.
- Launch it in the real target environment. Compilation, lint, or unit tests alone do not count.
- Confirm an observable successful startup. If that remains unverified, do not register anything.
- Use exactly one of the following forms. Keep
--provider codex; this skill must never attribute a program to Claude Code.
For a command:
node "$HOME/.octopus/bin/register-generated-program.js" --verified \
--name "Program name" \
--description "What the shortcut opens" \
--cwd "/absolute/project/path" \
--command "npm" --arg "run" --arg "dev" \
--provider codex
For an app bundle or directly openable file:
node "$HOME/.octopus/bin/register-generated-program.js" --verified \
--name "Program name" \
--cwd "/absolute/project/path" \
--open "/absolute/project/path/Program.app" \
--provider codex
- Add
--icon /absolute/pathonly when a suitable local icon already exists. - Report registration only after the command prints JSON with
"ok": true.
Boundaries
- Use absolute paths.
- If the registrar is missing, ask the user to open LLMPET Workbench → Generated Programs and authorize the Codex skill. Do not recreate LLMPET's registry format manually.
- Pass arguments as repeated
--argvalues. Do not embed shell pipelines in--command. - Register the canonical project once; the same path and launch command update the existing shortcut.
- Never pass
--verifiedbefore a real launch succeeds. - Registration changes only LLMPET's local shortcut index. It does not copy, deploy, publish, or delete the project.
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.
- 3d ago First seen · 49 lines · 71 tokens per session scan A b7847117e10e
register-generated-program is a skill published in the GitHub repository myunwang/LLMPET (112 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 495 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.
Other skills, from other repositories
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
extension-creator
Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.