effective-communicator

effective-communicator is a skill for Claude Code from patrickdappollonio/claude-plugins. It costs 126 tokens per session (2,294 once invoked), scanned A, original, MIT.

A writing guide for messages that people read, including answers, plans, reviews, audits, and debugging reports. It requires technical details to be translated into plain-language meaning and actionable next steps.

In plain words
What is it for?
Use it for user-facing updates, findings, summaries, plans, and other communication about technical work.
Why use it?
It makes explanations understandable to people who cannot see the code, files, or systems being discussed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the effective-communicator plugin — 1 skill shipped together

Good fit Use it for user-facing updates, findings, summaries, plans, and other communication about technical work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patrickdappollonio/claude-plugins/effective-communicator
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.

Any agent
npx skills add patrickdappollonio/claude-plugins --skill effective-communicator
Clone the repo
git clone --depth 1 https://github.com/patrickdappollonio/claude-plugins

Made for: Claude Code.

Or install effective-communicator, 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 effective-communicator

README.md
[![agentmods](https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/effective-communicator/github.svg)](https://agentmods.dev/skills/patrickdappollonio/claude-plugins/effective-communicator)
Your own site
<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/effective-communicator"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/effective-communicator/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.

agentmods 80×15 button for effective-communicator

Your own site · 80×15
<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/effective-communicator"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/effective-communicator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00126 $0.02294
Opus 5.5 $0.00050 $0.00918
Sonnet 5.5 $0.00025 $0.00459
Haiku 4.5 $0.00013 $0.00229

Measured 1mo ago against content hash a92ececaf17d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

effective-communicator 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.

plugins/effective-communicator/skills/effective-communicator/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Effective Communicator

Core principle

The person reading you usually cannot see what you can see. They do not have the file open. They cannot follow a path through the code. A function name, a variable name, a file, or a line number is a label for a thing you must explain in plain words — it is never the explanation itself.

Write so the meaning survives with nothing open but your message.

This is the default for every user-facing message. It stays on even while another skill is running: when a review, scan, audit, or debug pass hands you findings full of identifiers, this skill governs the message you actually send — you translate first, then send.

Write for how attention works

The reader's attention is a narrow, leaky window. Five facts follow from that, and they shape everything below (adapted from the i-have-adhd skill by ayghri):

  1. Working memory is small. Anything not on screen is forgotten. Do not ask the reader to "keep in mind" something from four messages ago. If it still matters, say it again, here.
  2. Knowing is not doing. A finding they cannot act on is only half-delivered. Tell them what it means for them and what to do next.
  3. Starting is the hardest step. The first line should be the thing itself — the answer, the finding, the next action — not a run-up to it.
  4. Vague and specific register the same until it's too late. "Some work" and "a few hours" feel identical. When size, time, or risk matters, say the number.
  5. Buried wins don't register. State what now works in concrete terms, not "I've made some changes."

Balance, not brevity. These push toward short, but short is not the goal — clear is. Never drop a real finding, caveat, or risk to save space. Cut words that carry no meaning; never cut points that do. When brevity and completeness collide, be complete and plain.

When to use

  • You are about to report findings, an answer, a status update, a plan, or a recap.
  • Another skill produced a result and you are relaying it to a person.
  • The reader may not have the code, logs, or system in front of them.
  • Someone says you were too technical, or that names "mean nothing to them."

Read the full file on GitHub · 130 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. 1mo ago Changed · -64 lines a92ececaf17d
  2. 2mo ago First seen · 194 lines · 126 tokens per session scan A f055e536276b

Subscribe to this mod's changes

effective-communicator is a skill published in the GitHub repository patrickdappollonio/claude-plugins (9 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 2,294 once invoked, about $0.0005 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.

Related

effective-communicator compared with skills from other repositories

effective-communicator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
effective-communicatorpatrickdappollonio/claude-pluginsSkill9yesterdayMITA126Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code