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 workspace-git-setupgit 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/workspace-git-setup)<a href="https://agentmods.dev/skills/songhonglei/better-agent-skills/workspace-git-setup"><img src="https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/workspace-git-setup/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/workspace-git-setup"><img src="https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/workspace-git-setup.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 | $0.00396 | $0.01588 |
| Opus 5.5 | $0.00158 | $0.00635 |
| Sonnet 5.5 | $0.00079 | $0.00318 |
| Haiku 4.5 | $0.00040 | $0.00159 |
Grade A, and why
workspace-git-setup 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workspace-git-setup
One command to set up safe, sensible Git tracking for any working directory — with a built-in security audit.
A zero-dependency Bash script that initializes Git version control for a project, ships a battle-tested security .gitignore, warns about large files before your first commit, and can audit an existing repo for leaked secrets and untracked files.
Pure bash + git. No Python, no npm, no third-party packages.
- Author: Evan Song · github.com/Songhonglei
- Repository: https://github.com/Songhonglei/better-agent-skills
- License: MIT
Usage
# Initialize / align config (defaults to current directory; auto-uses dir name as project name)
bash scripts/setup.sh
# Specify workspace path and project name
bash scripts/setup.sh /path/to/project "MyProject"
# Audit mode (read-only): detects sensitive files / untracked files / config
bash scripts/setup.sh --audit
# Dry-run mode: preview every action without applying anything
bash scripts/setup.sh --dry-run
Path & identity resolution
| Item | Priority |
|---|---|
| Workspace path | CLI argument > WORKSPACE_DIR env var > current directory |
| Git identity | GIT_AUTHOR_NAME / GIT_AUTHOR_EMAIL env vars > existing git config > interactive prompt |
When only an email is provided, the email prefix is used as the username (you can change it later with
git config).
Three modes
| Mode | What it does | Mutates? |
|---|---|---|
| (default) init / align | git init + writes safe .gitignore + large-file warning + first commit | ✏️ yes |
--audit |
read-only health check: tracked secrets / untracked files / core.autocrlf | 👀 no |
--dry-run |
preview every change without applying | 👀 no |
Default flow (init mode)
- Resolve path — CLI arg >
WORKSPACE_DIR> current directory - Infer project name — workspace basename (override with the 2nd argument)
- Read identity — env vars → existing git config → interactive prompt
- git init — skipped if a repo already exists (idempotent); sets
core.autocrlf=inputto unify line endings; default branchmain - Write
.gitignore— if one exists, shows a diff and asks before overwriting - Large-file warning — scans files >10MB to be tracked and asks for confirmation
- First commit — auto-stages and commits
- Summary — shows project name, path, git identity, and audit usage
What ships with it
4 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.
- 1mo ago First seen · 102 lines · 396 tokens per session scan A 0fa8d8a373d1
workspace-git-setup is a skill published in the GitHub repository Songhonglei/better-agent-skills (3 stars, last pushed 6d ago), licensed MIT. It adds 396 tokens to every session and 1,588 once invoked, about $0.0016 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 2026-08-31.
Other skills, from other repositories
release-rollback
Roll a release back for real when post-deploy regression goes red — apc release rollback flips the current version to pulled and the last good version back to current in the release ledger, and (with --mirror) repoints the bare mirror ref. Behind an approval gate; with no previous good version it BLOCKS instead of…
release-tag
Cut a release tag behind a real tier gate and cloud approval readback. The approval, task, approved commit, and resulting tag are bound; self-approval and HEAD drift fail closed. Prod prefixes remain refused.
git-ops
Close out a local coding task on the bound daemon — stage, commit, branch, merge, push via cloud git — and when a merge conflicts, STOP and escalate with the file list instead of auto-resolving. Push reaches only the bare replica; prod-triggering tags are refused.
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.
github-proxy
A tool that routes GitHub downloads through a proxy service, including repository clones, release files, raw files, and archives.
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.