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 Songhonglei/better-agent-skills --skill hello-envgit clone --depth 1 https://github.com/Songhonglei/better-agent-skillsWrote 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/songhonglei/better-agent-skills/hello-env)<a href="https://agentmods.dev/skills/songhonglei/better-agent-skills/hello-env"><img src="https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/hello-env/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/songhonglei/better-agent-skills/hello-env"><img src="https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/hello-env.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00233 | $0.01766 |
| Opus 5 | $0.00117 | $0.00883 |
| Sonnet 5 | $0.00047 | $0.00353 |
| Haiku 4.5 | $0.00023 | $0.00177 |
Grade A, and why
hello-env scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(git/curl/jq/make/docker) with paths and versions, network (hostname, IP, How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hello-env
- Version: 1.0.2
- License: MIT
- Author: Evan Song · github.com/Songhonglei
- Repository: https://github.com/Songhonglei/better-agent-skills
A zero-dependency Bash health check for any dev environment — host, container, or K8s pod.
一个零依赖的开源环境自检脚本，适用于本地、容器、K8s Pod 环境。
Pure bash. No Python, no npm, no third-party packages. Works on macOS, Linux, and inside containers.
Compatibility
| Platform | Status |
|---|---|
| Linux (any distro) | ✅ Full |
| macOS (bash 3.2.57+ default) | ✅ Full — uses eval-based indirect var expansion for bash 3.x |
| Windows (WSL / WSL2) | ✅ Full (effectively Linux) |
| Windows (Git Bash / MSYS / Cygwin) | ⚠️ Partial — OS/user/tools/network checks work; cgroup container detection and PVC monitoring are skipped (Linux-only kernel features) |
| Windows (PowerShell / cmd) | ❌ Not supported by design (bash script) |
| Agent Platform | Status |
|---|---|
| Claude Code | ✅ Standard SKILL.md, drops in |
| Codex | ✅ Same |
| OpenClaw | ✅ Native format |
| Cursor / Cline / others | ✅ Generic Markdown + bash, no platform hooks |
Quick start
# Run with defaults (current directory as workdir, default K8s probe vars)
bash scripts/check-env.sh
# Custom workdir
bash scripts/check-env.sh --workdir /opt/myapp
# Probe extra environment variables (comma-separated)
bash scripts/check-env.sh --probe-env "MY_REGION,MY_TIER,DEPLOY_ENV"
# Force PVC monitoring (when K8s probe vars are absent but you still want it)
bash scripts/check-env.sh --force-pvc
# Combine
bash scripts/check-env.sh \
--workdir /opt/myapp \
--watch-dir /opt/myapp/plugins \
--config /etc/myapp/config.json \
--probe-env "MY_REGION,MY_TIER" \
--force-pvc
What it checks
| # | Module | Output |
|---|---|---|
| 1 | OS | macOS / Linux distro + version |
| 2 | Current User | whoami + UID/GID |
| 3 | Node.js | Path (which node) + version |
| 4 | Python3 | Path + version |
| 5 | Basic Tools | git, curl, jq, docker, make — present / missing |
| 6 | Network | Hostname + IP + inferred private subnet (10.x / 172.16-31.x / 192.168.x) |
| 7 | Container / K8s | Probes configurable env vars; defaults to KUBERNETES_SERVICE_HOST + K8S_NAMESPACE; falls back to /.dockerenv / cgroup heuristics |
| 8 | Workdir | Path exists + git initialized check |
| 9 | Config file | Only checked if --config <path> provided |
| 10 | PVC persistence | Mount device-number + watch-dir count snapshot diff (auto when K8s probe hits, or --force-pvc) |
What ships with it
3 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.
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.
- 12d ago First seen · 182 lines · 233 tokens per session scan A 003a03a93991
hello-env is a skill published in the GitHub repository Songhonglei/better-agent-skills (3 stars, last pushed 4d ago), licensed MIT. It adds 233 tokens to every session and 1,766 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
ws-ckpt
A Linux-only tool for creating and managing workspace snapshots. A snapshot is a saved view of files that can later be compared, restored, listed, or deleted.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.