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 kgiwojno/g-sdd --skill g-setupgit clone --depth 1 https://github.com/kgiwojno/g-sddWrote 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/kgiwojno/g-sdd/g-setup)<a href="https://agentmods.dev/skills/kgiwojno/g-sdd/g-setup"><img src="https://agentmods.dev/badge/skills/kgiwojno/g-sdd/g-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/kgiwojno/g-sdd/g-setup"><img src="https://agentmods.dev/badge/skills/kgiwojno/g-sdd/g-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 | $0.00045 | $0.01789 |
| Opus 5 | $0.00023 | $0.00894 |
| Sonnet 5 | $0.00009 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade C, and why
g-setup scanned grade C 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
(`rm -rf .git/`), so it doesn't need a hard consent gate. How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior
1. Detect git
Run:
[ -d .git ]
- If
.git/exists, continue to step 2. - If
.git/is missing, continue to step 1a.
1a. Initialize git (only when .git/ is missing)
The g-sdd pipeline requires git. Tell the user what you're about to do:
This directory is not a git repository. The g-sdd pipeline requires
git. Initializing one here.
In an interactive session, you may pause and confirm before
proceeding if it feels natural ("OK to proceed?"). In auto mode,
just continue — git init is benign and trivially reversible
(rm -rf .git/), so it doesn't need a hard consent gate.
Run:
git init
If git init fails (e.g. git is not installed), abort with the
underlying error.
On success, print exactly:
✓ git initialized.
Please fully exit and restart Claude Code, then re-run /g-setup.
The g-sdd pipeline cannot continue without git, and Claude Code
needs a session restart to detect the new repository.
Then STOP. Do not continue to step 2 — scaffolding will happen on the next /g-setup run after the user restarts Claude Code.
2. Scaffold from manifest
The manifest lives at:
${CLAUDE_SKILL_DIR}/manifest.txt
Read and parse it. Each non-blank, non-# line is one of:
dir <path>— directory to create (relative to the project root).file <source> <destination>—<source>relative to${CLAUDE_SKILL_DIR}/,<destination>relative to the project root. Always overwrites on re-run.file-once <source> <destination>— same path semantics asfile, but strict create-if-absent: the destination is written only if it does not already exist. Used for content-bearing scaffolded files that operators populate after the first run (e.g.,CONTEXT.md). See "Notes" for the full strictness boundary.
Whitespace between fields is one or more spaces or tabs.
If the manifest is missing or unreadable, abort with:
Could not read ${CLAUDE_SKILL_DIR}/manifest.txt. The
g-sdd installation may be broken — reinstall g-sdd.
What ships with it
8 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.
- 9d ago First seen · 220 lines · 45 tokens per session scan C de8bec33075f
g-setup is a skill published in the GitHub repository kgiwojno/g-sdd (6 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 1,789 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…