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 agentmods add skills/yasuui/ystack/copy-skillnpx skills add Yasuui/ystack --skill copy-skillgit clone --depth 1 https://github.com/Yasuui/ystackWhat 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 | $0.00072 | $0.01915 |
| Opus 5 | $0.00036 | $0.00958 |
| Sonnet 5 | $0.00014 | $0.00383 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
copy-skill 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 yesterday.
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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Skill
The Fundamental Rule
Specificity beats adjectives. Every time.
"A powerful new tool for developers" is zero information. "Runs 7 agents in parallel on Gemini free tier" is a claim, a number, and a product detail in 8 words.
The test: can a competitor make the exact same claim without lying? If yes, rewrite it.
Voice: Yonis / Standard Bio.
This is not a corporate voice. It is a founder voice. Specific rules:
- First person or no person. No "we" (unless it's genuinely collaborative). "I built this" or "Built this" — not "We are excited to announce."
- Short declarative sentences. Not complex clauses. The period is powerful.
- Numbers when they exist. "40% faster" beats "significantly faster."
- No hedging. "This might help some developers who are looking for..." — never. "Solves X for Y" — always.
- Canadian, Toronto, indie, open source — these are identity markers. Use them when relevant.
- Technical terms are not jargon when the audience is technical. Do not dumb it down.
Platform Copy
X Posts (standalone — not thread)
Structure: one hook, one proof, one action or implication. Maximum 240 characters for the main post.
Hook patterns that work:
[Specific number or fact]: [implication]
"7 agents running in parallel. All on Gemini free tier."
[What I built] — [why it matters in one clause]
"Built a free alternative to gstack. Open source."
[The thing that surprised me] — [why]
"Plaid's Canadian coverage is actually solid. 90%+ of institutions."
[Before / after in two lines]
"Before: constant Gemini confirmations, $20/mo minimum
After: walk away and come back to a finished PR"
What to ban:
- Starting with "I'm thrilled/excited/proud to share..."
- "Game changer for..." (banned phrase)
- Rhetorical questions as hooks ("Have you ever wondered why...?") — weak
- Emoji as the first character — signals low signal-to-noise
- Thread-baiting ("here's what I learned 🧵") — earned by content, not promised
- Using the word "Just" to minimize your own work: "Just shipped a small thing..."
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.
- yesterday First seen · 202 lines · 72 tokens per session scan A 39aa00c998d5
copy-skill is a skill published in the GitHub repository Yasuui/ystack (1 stars, last pushed 5mo ago), licensed MIT. It adds 72 tokens to every session and 1,915 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 2026-08-31.
Other skills, from other repositories
env-scanner
Scan and audit Gemini CLI, Claude Code, Antigravity, Continue, Windsurf, JetBrains AI, and OpenCode environments. Discovers configurations, audits memory tiers, detects skill extraction state, analyzes behavioral tool chains, checks policy governance (v0.40+), and suggests reusable skills with evidence gating.…
scan
Scan your AI coding tool ecosystem — Gemini CLI, Claude Code, Antigravity (Desktop, CLI, IDE), Continue, Windsurf, JetBrains AI, OpenCode. Produces a maturity score, advisory recommendations, and optionally generates reusable SKILL.md files from your conversation patterns. Use when the user asks to audit their…
skill-parity
Keeps skills in sync across Claude Code, Codex, Gemini CLI, and shared .agents/skills paths. Handles copying, updating, pruning, and verifying parity across all provider locations. Trigger on: "sync my skills", "hydrate codex with skills", "copy skill to gemini", "add this skill to codex", "update skills across…
drupal-mental-model
Use when explaining code, debugging, or discussing architecture with Jack — map programming concepts to Drupal equivalents he already knows from years of Drupal/theming work. Triggers on code reviews, debugging walkthroughs, architecture discussions, inline code explanations, or whenever a non-Drupal framework concept…
appendix-agentic-frameworks
This skill should be used when the user wants to "choose agent framework", "compare LangChain vs LangGraph", "compare ADK vs LangGraph", "which framework to use for agents", "LangGraph tutorial", "CrewAI setup", "agentic framework comparison", "framework selection guide", "LangChain LCEL", "Google ADK tutorial"…
yapper
Yapper forces AI responses to be maximally verbose, thoroughly elaborated, and exhaustively explained. All output is expanded by 200–400%. Technical accuracy is maintained at 100%. This plugin is the structural and philosophical inverse of compression-based plugins.