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 ngreenwall/claude-skills --skill project-initgit clone --depth 1 https://github.com/ngreenwall/claude-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/ngreenwall/claude-skills/project-init)<a href="https://agentmods.dev/skills/ngreenwall/claude-skills/project-init"><img src="https://agentmods.dev/badge/skills/ngreenwall/claude-skills/project-init/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/ngreenwall/claude-skills/project-init"><img src="https://agentmods.dev/badge/skills/ngreenwall/claude-skills/project-init.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 | $0.00080 | $0.02351 |
| Opus 5.5 | $0.00032 | $0.00940 |
| Sonnet 5.5 | $0.00016 | $0.00470 |
| Haiku 4.5 | $0.00008 | $0.00235 |
Grade A, and why
project-init 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 2mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Project Init
Initialize a project so future sessions and handoffs work consistently in both Cursor and Claude Code. Default to the minimum: three docs plus git. A project earns more files by outgrowing these, not on day 0.
MISSION
Create the minimum durable scaffolding a project needs on day 0:
- Git repo initialized with a
.gitignore, and an MITLICENSEwhenever the project uses git CLAUDE.mdfor project-facing AI guidance, including a short "What this is" and "Key decisions" sectiondocs/WORKLOG.mdwith the task checklist (Now / Next) up top and rolling session notes belowREADME.mdbaseline sections so agents and humans can pick up the repo quickly.cursor/rules/context-router.mdfor Cursor startup routing
Do NOT create SPEC.md, DECISIONS.md, ROADMAP.md, or PROJECT.md. Spec and decision content starts as sections inside CLAUDE.md; the escalation path (below) covers projects that outgrow that.
PROTOCOL (run in this exact order)
Invoking this skill is the user's confirmation for its standard outputs: create the files for the chosen scope without per-file approval. Only two questions need answers at either scope: the scope question and the git question. This overrides any general "state proposed changes and wait for confirmation" habit for files this skill is defined to create.
Step 1: Determine project scope
Ask the user:
"Is this a simple, smaller project (a script, a one-off page, a config, a quick artifact), or an in-depth build (an app or tool you'll develop over time)?"
Do not infer the answer from file types or folder contents, only the user knows how deep this project goes. Exception: if the user already described the project's depth earlier in the conversation, state the scope you inferred and ask them to confirm instead of asking from scratch.
Simple project:
- Ask one setup question: "Will this live on git?"
- Yes: run
git initif not already a repo, create a minimal.gitignore(.DS_Store,.env,CLAUDE.local.md, plus stack-specific entries if detected), and create an MITLICENSE, all automatically, no further questions. Use a different license only if the user names one. Do NOT ask where it will be pushed or create a remote; the completion report covers connecting to GitHub later. After all files are created, make an initial commit (Initial scaffold) so the folder is push-ready. - No: skip git,
.gitignore, andLICENSEentirely.
- Yes: run
- Create or patch
README.mdwith just: What this is, How to install/use it, and any key configuration. Skip "How to run it" / "How to test or preview" if they don't apply. - Create a minimal
CLAUDE.mdso return sessions start oriented (it's the file AI tools auto-load), using the template inassets/claude-md-simple.md.
What ships with it
5 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.
- 2mo ago First seen · 149 lines · 80 tokens per session scan A 76026c0d649e
project-init is a skill published in the GitHub repository ngreenwall/claude-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 2,351 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 2026-08-31.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
dsh-pre-push-checks
A delivery-readiness check for software changes before they are pushed or released. It compares required checks with the actual source, build output, tests, and user-facing behavior.
managing-git
Manages Git workflows including branching, commits, and pull requests. Use when working with Git, creating commits, opening PRs, managing branches, resolving conflicts, or when asked about version control best practices.