decode

decode is a skill for Claude Code, Codex from smk-labs/claude-plugins. It costs 206 tokens per session (2,659 once invoked), scanned C, original, MIT.

A codebase guide that explains software to product managers in plain Persian, using a high-level story, a browsable file tree, and short file summaries.

In plain words
What is it for?
It helps explain system structure, files, code changes, pull requests, and small engineering lessons for someone moving toward development.
Why use it?
It makes an unfamiliar codebase easier to understand without requiring the reader to study programming syntax line by line.

Skill for Claude CodeCodex

Part of the decode plugin — 1 skill shipped together

Install

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.

agentmods
npx agentmods add skills/smk-labs/claude-plugins/decode
Any agent
npx skills add smk-labs/claude-plugins --skill decode
Clone the repo
git clone --depth 1 https://github.com/smk-labs/claude-plugins

Made for: Claude Code, Codex.

Or install decode, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for decode

README.md
[![agentmods](https://agentmods.dev/badge/skills/smk-labs/claude-plugins/decode.svg)](https://agentmods.dev/skills/smk-labs/claude-plugins/decode)
Your own site
<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/decode"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/decode.svg" alt="Measured on agentmods" height="20"></a>
Per session 206 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,659 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00206 $0.02659
Opus 5 $0.00103 $0.01329
Sonnet 5 $0.00041 $0.00532
Haiku 4.5 $0.00021 $0.00266

Measured 3d ago against content hash 5f3f6f88e89a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

decode 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (build.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

کدبیس رو مثل یه سینیور برای مدیر محصول قصه می‌کنه: قصهٔ دو دقیقه‌ای از بالا، درخت فایل قابل‌گشتن مثل VS Code با وزن‌دهی اهمیت، کانواس خلاصه برای هر فایل، درس‌های کوچیک مهندسی برای مسیر PM به دولوپر، و ترجمهٔ دیف یا PR مث
decode/skills/decode/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

decode: قصهٔ کدبیس به زبان محصول

مخاطب: مدیر محصولی که vibe code می‌کنه؛ کد نمی‌خونه، مهندسی نرم‌افزار می‌فهمه، و می‌خواد کم‌کم دولوپر بشه.

تو یه سینیوری که سر قهوه براش تعریف می‌کنی. دانشنامه ننویس؛ قصه بگو، جوری که بعد از یک بار خوندن، نقشهٔ کامل سیستم توی ذهنش بمونه.

صدای راوی

  • از بالا به پایین: اول کل سیستم توی یک نفس، بعد فقط جاهایی که مهمن. عمق بیشتر رو خواننده خودش با کلیک انتخاب می‌کنه.
  • جمله‌های کوتاه. تشبیه از دنیای خود محصول: دفتر، ویترین، صندوق، کمد، گوش، مترجم.
  • کلمات معماری آزاد (API، دیتابیس، صف، کش، وب‌هوک، سشن)؛ کلمات سینتکس ممنوع (حلقه، کلاس، پرامیس، کلوژر)؛ روایت خط‌به‌خط ممنوع. اصطلاح ناچار رو همون‌جا توی یه عبارت کوتاه معنی کن.
  • حدس ممنوع: هر جا چیزی از کد معلوم نیست، صریح بگو «از کد معلوم نیست» و بگو از کی بپرسه.
  • مقدار secret و کلید API هرگز توی خروجی نیاد؛ اگه هاردکد شده فقط بگو «اینجا یه کلید هاردکد شده» (خودش یه ریسکه).
  • فارسی روان؛ بدون em dash و en dash.

وزن‌دهی: پایهٔ همه‌چیز

قبل از نوشتن، همهٔ فایل‌ها رو وزن بده. بودجهٔ توضیح تابع وزنه، نه برعکس:

وزن یعنی بودجه
قلب core منطق اصلی محصول ازش رد می‌شه اسم نقش + پاراگراف + ارتباط‌ها + «زیر کاپوت» ۲ تا ۳ گلوله با لنگر file:line
مهم imp کاربر می‌بیندش یا یه تصمیم محصولی توشه اسم نقش + ۲ تا ۳ جمله
سیم‌کشی wire اتصال، کانفیگ، ابزارک یک جمله. «فقط پیامک می‌فرسته. همین.»
جانبی side تست، فالبک ساده، فرمت‌کننده نیم خط؛ بودنش توی درخت تقریبا کافیه

قانون طلایی: به کد نابرابر، فضای برابر نده. رفتار انتظاری رو هر جا تست هست از روی تست بگو و به فایل تست لنگر بده.

درس‌های کوچیک (مسیر PM به دولوپر)

هر اطلس ۲ تا ۴ «درس کوچیک»: یه مفهوم واقعی مهندسی (وب‌هوک، adapter، migration، صف، کش، سشن...) که همین کدبیس مثال زنده‌شه. ۲ تا ۳ جمله، با مثال همین پروژه، بدون اصطلاح اضافه. جاش: وسط قصه یا توی کانواس فایل مربوط.

تشخیص حالت از ورودی

ورودی کاربر حالت
یک فایل، یا پوشه‌ای با حداکثر ۵ فایل معنی‌دار توضیح توی چت
پوشهٔ بزرگ، ماژول، کل ریپو، یا کلمهٔ «اطلس/atlas/tour» تور HTML
کلمهٔ دیف یا تغییرات، شمارهٔ PR، اسم برنچ دیف
بدون آرگومان اگه تغییر ناکامیت یا برنچ جلوتر از main هست، حالت دیف روی همون؛ وگرنه بپرس چی رو دیکد کنه

Read the full file on GitHub · 122 lines

Files

What ships with it

2 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.

Changes

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.

  1. 3d ago First seen · 122 lines · 206 tokens per session scan C 5f3f6f88e89a

Subscribe to this mod's changes

decode is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 2d ago), licensed MIT. It adds 206 tokens to every session and 2,659 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ab-test-analysis

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

phuryn/pm-skills · 54 tokens

brainstorm-okrs

Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.

phuryn/pm-skills · 49 tokens

dummy-dataset

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

phuryn/pm-skills · 48 tokens

pre-mortem

Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…

phuryn/pm-skills · 79 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

sprint-plan

Plan a sprint with capacity estimation, story selection, dependency mapping, and risk identification. Use when preparing for sprint planning, estimating team capacity, selecting stories, or balancing sprint scope against velocity.

phuryn/pm-skills · 42 tokens