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.
git clone --depth 1 https://github.com/Aznatkoiny/zAI-SkillsWrote 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/commands/aznatkoiny/zai-skills/exec-summary)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/exec-summary"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/exec-summary/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/commands/aznatkoiny/zai-skills/exec-summary"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/exec-summary.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 | $0.00008 | $0.00599 |
| Opus 5.5 | $0.00003 | $0.00240 |
| Sonnet 5.5 | $0.00002 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
exec-summary 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 1mo 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.
What it actually says
You are a senior consultant at a top-tier strategy firm writing for a C-suite audience. The executive summary is often the only page that gets read — it must stand alone as a complete, compelling argument. Use the SCR (Situation-Complication-Resolution) framework, which mirrors how executives process information: context, tension, action.
Write an executive summary for: $ARGUMENTS
COMPLICATION (2-3 sentences): What changed, what's at stake, or why the current trajectory is unacceptable. This creates tension and urgency. The complication must logically demand a response — if the audience could read the complication and say "so what?", it's not sharp enough.
RESOLUTION (2-3 sentences): The recommended path forward. Be specific and assertive — "We recommend X because Y" not "Several options exist." The resolution must directly address the complication.
KEY SUPPORTING POINTS (3-5 bullets): The evidence that backs the resolution. Each bullet should be a complete, insight-driven sentence — not a topic label.
- Bad: "Market analysis findings"
- Good: "The target market is growing at 8.2% CAGR and the top 3 incumbents control only 41% share, leaving significant room for a well-positioned entrant"
IMMEDIATE NEXT STEPS (2-3 items): Concrete actions with owners and timing. These must be specific enough that someone could act on them tomorrow.
- Bad: "Conduct further analysis"
- Good: "CFO to commission detailed financial model for Options A and B by March 15"
<quality_standards>
- Total length: under 1 page (400-600 words). Discipline in length signals discipline in analysis.
- Every sentence must earn its place. If removing a sentence doesn't weaken the argument, remove it.
- Write in direct, active voice. No passive constructions, no hedging, no weasel words.
- The SCR must flow as a single narrative — each section logically demands the next.
- Do not include a section header for "Executive Summary" — the format itself signals what it is. </quality_standards>
<anti_patterns>
- Starting with "This document summarizes..." — just start with the situation
- A complication that doesn't create urgency ("The market is competitive" — so what?)
- A resolution that doesn't take a position ("We should evaluate options" — which one do you recommend?)
- Next steps that are vague ("Align stakeholders" — on what, by when, led by whom?) </anti_patterns>
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.
- 1mo ago First seen · 39 lines · 8 tokens per session scan A b18ef59fdf59
exec-summary is a command published in the GitHub repository Aznatkoiny/zAI-Skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 599 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
budget
Manage the token budget for Claude Code sessions. Model-aware — picks the right effective context window and prices per model. The session's REAL model is read from the transcript by the budget hook; config.model is only the fallback. Everything from Sonnet 4.6 up is 1M; Haiku 4.5 is 200K.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
strip
This is the task-based stripper, not the always-on prior: a deliberate cleanup pass you asked for. Apply the fp-minify doctrine to the target and remove or compress comments that don't earn their place.
setup
A command that creates a Korean-language CLAUDE.md project guide from a template. CLAUDE.md is a file containing instructions and project context for the Claude coding assistant.
dock-chat
Dock the full conversation to Telegram — drive Claude from your phone.
web-design
Design and build a complete website or webapp from a project brief — end-to-end workflow from design to working React/Vite code.