Borrowing it
Nothing to install: this file belongs to ivaaaan/smug. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ivaaaan/smug/master/.claude/skills/new-config/SKILL.mdgit clone --depth 1 https://github.com/ivaaaan/smugWrote 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/ivaaaan/smug/new-config)<a href="https://agentmods.dev/skills/ivaaaan/smug/new-config"><img src="https://agentmods.dev/badge/skills/ivaaaan/smug/new-config/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/ivaaaan/smug/new-config"><img src="https://agentmods.dev/badge/skills/ivaaaan/smug/new-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 11 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 88 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00086 | $0.01171 |
| Opus 5 | $0.00043 | $0.00585 |
| Sonnet 5 | $0.00017 | $0.00234 |
| Haiku 4.5 | $0.00009 | $0.00117 |
Grade A, and why
new-config 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 10d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a new smug configuration
Scaffold a new smug session config by interviewing the user with the
AskUserQuestion tool, then writing a valid YAML file in the smug format.
Do not write the file until you have asked the questions below. Ask in small batches, infer sensible defaults, and only ask what you can't infer.
1. Gather requirements (interactive)
Ask with AskUserQuestion. Group related questions into a single call when you
can. Always offer a clear default and let the user override via "Other".
- Session name — the tmux session name (
session:). Suggest the current directory's basename as the default. - Where to save — one of:
.smug.ymlin the current working directory (used by default bysmug).~/.config/smug/<session>.yml(loadable assmug start <session>).- A custom path the user types.
- Root directory — the session
root:(where windows start). Default.for a cwd config, or the cwd's absolute path for a~/.config/smugconfig. - Windows — ask how many windows and, for each, the name and what it runs (e.g. "editor", "server", "tests"). Keep it light; one window with a command is a fine minimal config. Only dig into panes/layout if the user wants a split window.
- Optional extras — only ask if the user signals they want them:
attach: true(auto-attach after creation).env:variables.before_start:/stop:commands (e.g.docker-compose up -d).attach_hook:/detach_hook:.
If the user says "just give me a basic one" or similar, skip straight to a minimal config (session + root + one window) — don't force the full interview.
2. Smug config schema (reference)
Generate YAML matching this structure. Omit empty/optional fields.
session: my_project # tmux session name (required)
root: ~/code/my_project # base dir for the session
attach: true # optional: auto-attach after creation (default false)
env: # optional: environment variables
FOO: bar
before_start: # optional: runs once before the session is created
- docker-compose up -d
stop: # optional: runs once before the session is killed
- docker-compose stop
attach_hook: echo hi # optional: runs each time first client attaches
detach_hook: echo bye # optional: runs each time last client detaches
windows:
- name: code # window name
root: . # optional: path relative to session root
selected: true # optional: focus this window on start
manual: false # optional: only start via `-w` when true
layout: main-vertical # optional: tmux layout (e.g. tiled, main-horizontal)
commands: # commands run in the window's first pane
- $EDITOR .
panes: # optional: extra split panes
- type: horizontal # horizontal | vertical
root: . # optional
commands:
- npm run dev
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.
- 10d ago First seen · 105 lines · 86 tokens per session scan A adb235475499
new-config is a skill published in the GitHub repository ivaaaan/smug (911 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,171 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
conventional-commit
Workflow for generating conventional commit messages following the Conventional Commits specification. MUST be invoked every time a commit is created. Guides construction of standardized commit messages with correct type, scope, description, body, and footer.
segment-create
Full scaffolding workflow for creating a new Oh My Posh segment. Invoke when asked to add a new segment: generates the Go source, registers the type, creates documentation, updates the sidebar and JSON schema.
date-formatter
Converts dates between formats and handles timezone differences.
log-work
Log the work segment that you did after the last work log until now in a.
redux-to-swr
Migrate React components from Redux + Saga to SWR hooks. Use when converting data fetching from Redux store (reducers, sagas, selectors, connect HOC) to SWR-based hooks in CockroachDB DB Console or cluster-ui.
mma-investigator
Expert system for investigating MMA (Multi-Metric Allocator) behavior on CockroachDB clusters. Helps oncall engineers diagnose load imbalances, understand rebalancing decisions, and identify why MMA did or didn't act.