Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add davistroy/claude-marketplace/plugin install personal-pluginWrote 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/davistroy/claude-marketplace/new-project)<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/new-project"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/new-project/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/davistroy/claude-marketplace/new-project"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/new-project.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 | $0.00077 | $0.02933 |
| Opus 5 | $0.00039 | $0.01466 |
| Sonnet 5 | $0.00015 | $0.00587 |
| Haiku 4.5 | $0.00008 | $0.00293 |
Grade A, and why
new-project 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 7d 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.
allowed-tools: Bash(mkdir:*), Bash(cd:*), Bash(git:*), Bash(gh:*), Bash(bws:*), Bash(python3:*), Bash(curl:*), Bash(unset:*), Bash(date:*), Bash(echo:*), Read, Write, Edit, Glob How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Project
Scaffold a new project at ~/dev/<org>/<name> with everything a project needs on day one: an initialized git repo with a remote, a project CLAUDE.md seeded from the house template, a type-appropriate .gitignore, a placeholder-only .env, a mandatory LAB_NOTEBOOK.md, a kill-criteria BRIEF.md, and an initial commit pushed to the new remote.
This is a side-effect-only skill (disable-model-invocation: true) — it never runs proactively. Invoke it explicitly: /new-project <org>/<name> [--type python|node|docs] [--gitea].
Input
Arguments: $ARGUMENTS
Expected form: <org>/<name> [--type python|node|docs] [--gitea]
<org>— one ofcfa,personal,stratfield,cgi. Selects the target directory~/dev/<org>/.<name>— kebab-case project name. Becomes the directory name and the GitHub/Gitea repo name.--type python|node|docs— optional. Selects the.gitignoretemplate (Step (d)). Omit for a minimal generic.gitignore.--gitea— optional. Create the remote on the shared Gitea instance instead of GitHub (Step (b)).
Validation (before doing anything else)
- Parse
<org>/<name>from the first argument token. If it doesn't matchorg/nameshape, stop and ask for it in that form. <org>must be exactly one ofcfa,personal,stratfield,cgi. If not, stop:Error: org must be one of cfa, personal, stratfield, cgi (got '<org>').- If
--typeis given, its value must be exactly one ofpython,node,docs. If not, stop:Error: --type must be one of python, node, docs (got '<value>'). - Abort if
~/dev/<org>/<name>already exists — do not touch, merge into, or overwrite an existing directory. Report the existing path and stop.
Instructions
Execute the steps below in order. Steps (g) and (i) have a real dependency: the lab-notebook init in (g) creates a fresh LAB_NOTEBOOK.md entry, which is what satisfies the lab-notebook-gate pre-commit hook's "entry within 24h" check for the commit in (i). Do not reorder (i) ahead of (g).
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.
- 7d ago First seen · 229 lines · 77 tokens per session scan A e746f7d8e82d
new-project is a skill published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 2,933 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
gsd-pause-work
Create context handoff when pausing work mid-phase.
gsd-ship
Create PR, run review, and prepare for merge after verification passes.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.