Borrowing it
Nothing to install: this file belongs to florian101010/awesome-agentic-AI-coding-template. 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/florian101010/awesome-agentic-AI-coding-template/main/.agent/skills/setup-repo/SKILL.mdgit clone --depth 1 https://github.com/florian101010/awesome-agentic-AI-coding-templateWrote 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/florian101010/awesome-agentic-ai-coding-template/setup-repo)<a href="https://agentmods.dev/skills/florian101010/awesome-agentic-ai-coding-template/setup-repo"><img src="https://agentmods.dev/badge/skills/florian101010/awesome-agentic-ai-coding-template/setup-repo/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/florian101010/awesome-agentic-ai-coding-template/setup-repo"><img src="https://agentmods.dev/badge/skills/florian101010/awesome-agentic-ai-coding-template/setup-repo.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 | $0.00054 | $0.02687 |
| Opus 5 | $0.00027 | $0.01344 |
| Sonnet 5 | $0.00011 | $0.00537 |
| Haiku 4.5 | $0.00005 | $0.00269 |
Grade A, and why
setup-repo 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 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.
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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Repo
Overview
This skill produces a fully configured repo with zero remaining [FILL:] markers. It covers all 32 files that contain markers — not just the primary instruction files — and writes them directly when run in Claude Code.
Announce at start: "I'm using the setup-repo skill. I'll ask you 3 quick questions, then read the codebase and write all instruction files."
When to Use
- Immediately after cloning this template into a new project
- When basic fills were done manually but deeper fills remain
- When onboarding an existing codebase onto this template
When NOT to Use
- Repo already fully set up (verify:
grep -rn "\[FILL:" . --include="*.md"returns nothing outside docs) - You only need to update one specific file — edit it directly instead
Execution Modes
Mode A — Claude Code (preferred)
Claude Code has direct file access. The skill reads files, gathers facts, writes every file in place, activates git hooks, and validates. No copy-pasting required.
Mode B — Other agents
Generate a repo bundle first:
npx repomix # produces repomix-output.xml (already configured)
Attach repomix-output.xml to your chat. The skill outputs filled content tiered by priority — paste and apply Tier 1 before proceeding to Tier 2.
Phase 0 — Ask 3 Questions
Before reading a single file, ask the user these questions. Their answers fill things no codebase analysis can determine:
Question 1 — Users & deployment context:
"Who are the primary users of this project and what is the deployment environment?" (e.g. "Internal logistics staff via a React dashboard", "Public API consumers", "iOS/Android WebView")
Question 2 — Immutable contract:
"Are there any externally-bound IDs, stored data schemas, or API versions that MUST NEVER change — even across refactors?" (If yes, list them. If no, answer "none" — the Immutable Contract section will be deleted.)
Question 3 — Extra prohibitions:
"Is there anything agents should never do that won't be obvious from reading the code?" (e.g. "Never modify the payments module without a second review", "Never add browser APIs — this runs in a Node.js CLI")
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 · 262 lines · 54 tokens per session scan A b52748912847
setup-repo is a skill published in the GitHub repository florian101010/awesome-agentic-AI-coding-template (4 stars, last pushed 6mo ago), licensed MIT. It adds 54 tokens to every session and 2,687 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
arxiv
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
analyzing-network-covert-channels-in-malware
Detect and analyze covert communication channels used by malware including DNS tunneling, ICMP exfiltration, steganographic HTTP, and protocol abuse for C2 and data exfiltration.
analyzing-windows-lnk-files-for-artifacts
Parse Windows LNK shortcut files to extract target paths, timestamps, volume information, and machine identifiers for forensic timeline reconstruction.
analyzing-powershell-script-block-logging
Parse Windows PowerShell Script Block Logs (Event ID 4104) from EVTX files to detect obfuscated commands, encoded payloads, and living-off-the-land techniques. Uses python-evtx to extract and reconstruct multi-block scripts, applies entropy analysis and pattern matching for Base64-encoded commands, Invoke-Expression…
analyzing-command-and-control-communication
Analyzes malware command-and-control (C2) communication protocols to understand beacon patterns, command structures, data encoding, and infrastructure. Covers HTTP, HTTPS, DNS, and custom protocol C2 analysis for detection development and threat intelligence. Activates for requests involving C2 analysis, beacon…
analyzing-usb-device-connection-history
Investigate USB device connection history from Windows registry, event logs, and setupapi logs to track removable media usage and potential data exfiltration.