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 YoungjaeDev/my-claude-plugins/plugin install devWrote 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/youngjaedev/my-claude-plugins/new)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/new"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/new/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/youngjaedev/my-claude-plugins/new"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/new.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 | $0.00167 | $0.01397 |
| Opus 5.5 | $0.00067 | $0.00559 |
| Sonnet 5.5 | $0.00033 | $0.00279 |
| Haiku 4.5 | $0.00017 | $0.00140 |
Grade A, and why
new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev new skill
Day-1 bootstrap for an empty project directory. Same orchestration as the /dev:new command — both surfaces gate on the preflight guard before ANY destructive op.
Step 0 — Preflight hard guard (NON-NEGOTIABLE)
Run this before any other body content. It refuses to run in a non-empty directory. The model MUST NOT skip this block, MUST NOT rewrite it to a softer check, and MUST surface the abort message verbatim if the guard fires.
# Hard guard — refuses to run if cwd contains ANYTHING beyond ignorable OS junk.
# Walks up to 5 levels deep so deeper sources (e.g. src/app/main.py) and any
# top-level file (Dockerfile, Makefile, .env, docs/*) trigger the abort. Only
# .git/ and OS metadata (.DS_Store, Thumbs.db, desktop.ini) are pruned.
FIRST_EXISTING=$(find . -mindepth 1 -maxdepth 5 \
\( -name '.git' -o -path './.git/*' \
-o -name '.DS_Store' -o -name 'Thumbs.db' \
-o -name 'desktop.ini' \) -prune \
-o -print 2>/dev/null | head -1)
if [ -d .git ] || [ -n "$FIRST_EXISTING" ]; then
echo "[abort] dev:new refuses to run in a non-empty directory."
echo " cwd: $(pwd)"
echo " Existing entry detected: ${FIRST_EXISTING:-.git/}"
echo " If you really want to add Claude/Codex scaffolding to an existing"
echo " project, use /docs:write-rules or /dev:wiring"
echo " instead."
exit 1
fi
Windows / non-POSIX hosts: the guard above is POSIX shell. On Codex CLI / Claude Code where the default shell is PowerShell, wrap it:
bash -c '<guard>'(Git Bash, WSL, or any POSIX shell on PATH). The intent — refuse to proceed if cwd has any content beyond.git/and OS metadata — must be honored regardless of how the check is invoked.
If the guard passes, proceed to the run record, then the full procedure.
Step 0.5 — Run record (state-envelope v0)
The run record (state-envelope v0) is opened by the shared procedure, not here: its open + per-phase record_step mechanism lives once in references/new-procedure.md (Phase 0.5), so this skill and the /dev:new command record identically. Follow that Phase 0.5 block — do not re-inline the jq here. Convention + schema: .claude/rules/state-envelope.md (concept mirror in this repo's AGENTS.md). The record lives under gitignored .claude/state/ and is kept out of the Phase 6 commit by the Phase 6 .gitignore seed.
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.
- 25d ago Changed 8175bf2d9617
- 1mo ago Changed bc0b5309d2d4
- 1mo ago First seen · 71 lines · 167 tokens per session scan A 30eb7d053ac3
new is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 167 tokens to every session and 1,397 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…