wise-human-writing

wise-human-writing is a skill for Claude Code from e1024kb/wise-claude. It costs 281 tokens per session (2,940 once invoked), scanned A, original, MIT.

A set of plain-language rules for writing messages that other people will read, including tickets, pull requests, review comments, documentation, and chat updates.

In plain words
What is it for?
Use it when drafting or rewriting project updates, issue descriptions, code-review replies, pull requests, documentation, or messages in team communication tools.
Why use it?
It keeps messages focused on what happened, why it matters, and what comes next instead of exposing a messy work log or too much technical detail.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the wise plugin — 38 skills, 13 agents, 1 hook, 1 MCP server shipped together

Good fit Use it when drafting or rewriting project updates, issue descriptions, code-review replies, pull requests, documentation, or messages in team communication tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/e1024kb/wise-claude/wise-human-writing
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 e1024kb/wise-claude --skill wise-human-writing
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude

Made for: Claude Code.

Or install wise, the plugin that ships this one along with the rest of its 38 skills, 13 agents, 1 hook, 1 MCP server.

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 wise-human-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-human-writing/github.svg)](https://agentmods.dev/skills/e1024kb/wise-claude/wise-human-writing)
Your own site
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-human-writing"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-human-writing/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 wise-human-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-human-writing"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-human-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 281 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,940 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 $0.00281 $0.02940
Opus 5 $0.00140 $0.01470
Sonnet 5 $0.00056 $0.00588
Haiku 4.5 $0.00028 $0.00294

Measured 9d ago against content hash 16de7294dcfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wise-human-writing 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 9d 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/wise/skills/wise-human-writing/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wise-human-writing - write for humans, not for logs

Why this skill exists

Messages generated straight from a work session read like the work session: exhaustive, symbol-heavy, structureless. The reader of a Jira comment or a Slack update was not in that session. They need the story - what happened, why, what's next - in the order a human tells it, at the altitude a human cares about. This skill is the standing contract for every outbound message: it defines the structure, the altitude, and the per-tool formatting so that anything posted on the user's behalf reads like a sharp colleague wrote it.

Two ways this skill runs

  1. Standing reference (the main mode). Consult these rules automatically whenever composing content that will land in front of other humans through an external tool: ticket descriptions, tracker comments, PR/MR descriptions or comment replies, doc pages, chat messages. It does not matter which tracker, code host, doc system, or chat product is in play, or whether the write happens through an MCP server, a CLI (gh, glab, jira, linear), or a raw API call - if a human will read it in another tool, these rules apply.
  2. Slash rewrite - /wise-human-writing [<draft>]. The user pastes a draft (or points at a file / a message earlier in the conversation) and gets back a cleaned version. This form never posts anywhere - it returns text and stops.

Arguments (slash form only)

Parse $ARGUMENTS as one free-form value:

Input Behaviour
Draft text inline Rewrite it per the rules below; return the result.
A file path Read the file, rewrite its content, return the result. Do not modify the file.
A pointer ("the comment above", "my last Slack draft") Locate that text in the conversation, rewrite, return.
(empty) If an outbound message is currently being drafted, apply the rules to it. Otherwise summarize the rules in three lines and ask what to rewrite.

Read the full file on GitHub · 263 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. 9d ago First seen · 263 lines · 281 tokens per session scan A 16de7294dcfb

Subscribe to this mod's changes

wise-human-writing is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed yesterday), licensed MIT. It adds 281 tokens to every session and 2,940 once invoked, about $0.0014 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.

Related

Other skills, from other repositories

docs-drift

Documentation-drift audit for this plugin monorepo. Audit either each scoped plugin's unreleased changelog claims or its latest shipped release from the previous reachable plugin-name--v tag, then verify that plugin READMEs, docs, CLAUDE.md or AGENTS.md files, and root documentation tell the truth for the matching…

gtapps/claude-code-hermit · 170 tokens

cco-tools

Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.

egorfedorov/claude-context-optimizer · 27 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens

test-run

Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.

gtapps/claude-code-hermit · 35 tokens

design-system-reference

Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.

wigtn/wigtn-plugins · 43 tokens

magic-compact

Compact this Claude Code session.

aerovato/magic-compact · 10 tokens