tighten-this

tighten-this is a skill for Claude Code from skilletmd/skillet. It costs 52 tokens per session (532 once invoked), scanned A, original, Apache-2.0.

An editing pass that removes unnecessary words from drafts while keeping their meaning. It works on writing such as emails, documents, posts, messages, and pull-request descriptions.

In plain words
What is it for?
Putting the request first, removing empty introductions and hedging, using direct sentences, and separating multiple ideas.
Why use it?
It makes the main point easier to see when a draft is padded, indirect, or difficult to follow.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Putting the request first, removing empty introductions and hedging, using direct sentences, and separating multiple ideas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skilletmd/skillet/tighten-this
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 skilletmd/skillet --skill tighten-this
Clone the repo
git clone --depth 1 https://github.com/skilletmd/skillet

Made for: Claude Code.

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 tighten-this

README.md
[![agentmods](https://agentmods.dev/badge/skills/skilletmd/skillet/tighten-this/github.svg)](https://agentmods.dev/skills/skilletmd/skillet/tighten-this)
Your own site
<a href="https://agentmods.dev/skills/skilletmd/skillet/tighten-this"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/tighten-this/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 tighten-this

Your own site · 80×15
<a href="https://agentmods.dev/skills/skilletmd/skillet/tighten-this"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/tighten-this.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 532 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 $0.00052 $0.00532
Opus 5 $0.00026 $0.00266
Sonnet 5 $0.00010 $0.00106
Haiku 4.5 $0.00005 $0.00053

Measured 11d ago against content hash fb82c157eca8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tighten-this 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 11d 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.

skills/tighten-this/SKILL.md · 46 lines

What it actually says

tighten-this

First drafts carry padding the idea doesn't need. Keep the ideas; cut the words around them. This skill is one editing pass: keep the meaning, cut the padding, surface the point.

When to use

Any draft that feels long or buried — an email, a doc, a PR description, a message, a launch post. Run it after the draft exists, not while you're writing.

The pass

1. Put the point first

Find the one sentence that says what you actually want. Move it to the top. If a reader stops after the first line, they should still get the message.

2. Cut the throat-clearing

Delete openers that carry no information:

  • "I just wanted to reach out to..." → start with the ask.
  • "It's worth noting that..." → just note it.
  • "In order to" → "to". "At this point in time" → "now". "Due to the fact that" → "because".

3. Drop the hedges

"I think maybe we could possibly" says nothing. Pick one: you recommend it or you don't. Hedging reads as insecure or evasive.

4. Active voice, real subject

"A decision was made to delay" → "We delayed." Name who does what. Passive voice hides the actor and adds words.

5. One idea per sentence

A sentence with two "and"s and a "which" is usually three sentences crammed into one. Break it up. Short sentences are easier to trust.

6. Replace adjectives with the fact behind them

"Blazingly fast" tells the reader nothing; "under 200ms" does. When you reach for an adjective, ask what made you reach for it, and write that instead.

The read-aloud test

Read the result out loud. Anywhere you stumble, run out of breath, or sound like a press release — rewrite that line. If a sentence survives only because it sounds nice, cut it.

What not to do

  • Don't flatten a personal message into a telegram. Concise is the goal; curt is not.
  • Don't cut the one caveat that keeps a claim honest. Tightening removes padding, not truth.
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. 11d ago First seen · 46 lines · 52 tokens per session scan A fb82c157eca8

Subscribe to this mod's changes

tighten-this is a skill published in the GitHub repository skilletmd/skillet (3 stars, last pushed 11d ago), licensed Apache-2.0. It adds 52 tokens to every session and 532 once invoked, about $0.0003 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.