explain-dev

explain-dev is a command for coding agents from Jewgah/claude-code-skills. It costs 16 tokens per session (1,031 once invoked), scanned A, original, MIT.

A command that turns development updates into short, non-technical WhatsApp messages for clients. It explains the user-facing result and distinguishes work that is already delivered from work that is only planned.

In plain words
What is it for?
Use it to describe completed or planned features, group related changes, and give clients simple instructions for checking the result.
Why use it?
It removes the need to translate technical tasks into client-friendly language manually. It also helps prevent messages from implying that unfinished work is already live.

Command

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 commands/jewgah/claude-code-skills/explain-dev
Clone the repo
git clone --depth 1 https://github.com/Jewgah/claude-code-skills

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 explain-dev

README.md
[![agentmods](https://agentmods.dev/badge/commands/jewgah/claude-code-skills/explain-dev.svg)](https://agentmods.dev/commands/jewgah/claude-code-skills/explain-dev)
Your own site
<a href="https://agentmods.dev/commands/jewgah/claude-code-skills/explain-dev"><img src="https://agentmods.dev/badge/commands/jewgah/claude-code-skills/explain-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,031 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00016 $0.01031
Opus 5 $0.00008 $0.00515
Sonnet 5 $0.00003 $0.00206
Haiku 4.5 $0.00002 $0.00103

Measured 3d ago against content hash bfb1ea74a67b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explain-dev 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 3d 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.

commands/explain-dev.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write a concise, non-technical, copy-paste-ready WhatsApp message explaining the development discussed or delivered in this conversation. Translate technical work into client benefits.

Language: en by default. If $ARGUMENTS starts with fr, write it in French instead, using the French strings in the table below. Everything else about the format is identical.

Step 1 — determine the dev's STATUS before writing anything. Scan the conversation for signs it is ALREADY shipped (commit made, pushed, merged, deployed, delivered, tests green in prod) versus only PLANNED/discussed. The status drives the whole message:

  • Already shipped → past/present tense ("I added…", "the form now has…", "you can now…"). Never future or conditional. The test section is titled How to test — it's live, so never "once delivered".
  • Planned → near-future tense, and the test section keeps the "once delivered" title.
  • When in doubt (no sign of delivery), treat it as PLANNED.

Step 2 — build the message.

  1. Identify the tasks/features involved.
  2. Group them by theme when it helps.
  3. Turn each technical task into a client/user benefit.
  4. Add a short test section describing how the client checks it themselves.

Fixed strings

Slot English French
Greeting (shipped) *Update delivered - [Theme]* *Mise a jour livree - [Thème]*
Greeting (planned) *Update planned - [Theme]* *Mise a jour prevue - [Thème]*
Test title (shipped) *How to test* *Comment tester*
Test title (planned) *How to test once delivered* *Comment tester une fois livre*
Closing line Don't hesitate if you have any questions. N'hesitez pas si vous avez des questions.

Format rules

  • WhatsApp formatting only: *bold* for titles. No markdown headings.
  • Open with the greeting line for the detected status (table above).
  • List each major change as a *bold* number followed by 1-2 explanatory dashes.
  • Keep dashes SHORT (1 line max) in language a non-technical reader understands.
  • End with the test section, then the closing line.
  • NO technical jargon: no file names, no function names, no code, no "API", no "script", no "migration", no "database", no "SQL", no "bug fix".
  • No emojis.
  • NEVER use an em dash (—), en dash (–) or arrow (→) — they read as AI-written. Use a comma, a period, parentheses, or the word "to" instead.
  • ~25 lines maximum. Stay concise but leave room for the test section.
  • Output ONLY the message. No preamble, no explanation, no commit hashes, no ticket links.

Read the full file on GitHub · 89 lines

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 · 89 lines · 16 tokens per session scan A bfb1ea74a67b

Subscribe to this mod's changes

explain-dev is a command published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,031 once invoked, about $0.0001 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.