skill-tighten

skill-tighten is a skill for Claude Code from techygarg/lattice. It costs 123 tokens per session (1,518 once invoked), scanned A, original, MIT.

A tool that rewrites SKILL.md instruction files so their rules are shorter, clearer, and more direct.

In plain words
What is it for?
Use it to tighten one skill file, a group of skills, or all skills, then receive a report of the wording changes and a cleanliness check.
Why use it?
It reduces the chance that an AI coding agent will overlook instructions because they are softened by explanations, vague wording, or repetition.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the lattice plugin — 33 skills, 1 agent shipped together

Good fit Use it to tighten one skill file, a group of skills, or all skills, then receive a report of the wording changes and a cleanliness check.

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

Made for: Claude Code.

Or install lattice, the plugin that ships this one along with the rest of its 33 skills, 1 agent.

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 skill-tighten

README.md
[![agentmods](https://agentmods.dev/badge/skills/techygarg/lattice/skill-tighten.svg)](https://agentmods.dev/skills/techygarg/lattice/skill-tighten)
Your own site
<a href="https://agentmods.dev/skills/techygarg/lattice/skill-tighten"><img src="https://agentmods.dev/badge/skills/techygarg/lattice/skill-tighten.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,518 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00123 $0.01518
Opus 5 $0.00062 $0.00759
Sonnet 5 $0.00025 $0.00304
Haiku 4.5 $0.00012 $0.00152

Measured 3d ago against content hash 629987dbef50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skill-tighten 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.

dev-skills/skill-tighten/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Tighten

Core responsibility: Fix language that causes agents to skip or underweight instructions. Not behavioral gaps — that is skill-review's job. Only phrasing: rationale prose, soft language, missing enforcement signals, redundant repetition.

Input: One or more of:

  • A file path: source/atoms/clean-code/SKILL.md
  • A skill name: clean-code (resolves to the correct path automatically)
  • A tier: atoms (tightens all skills in that tier)
  • No argument: tightens all skills across all tiers

Output: Edited files + a report per skill:

## skill-tighten — {skill-name}
Lines: {before} → {after}
Changes:
1. {what changed} — {one-line reason}
2. ...
Result: TIGHTENED ({N} changes) | CLEAN (no changes needed)

How to verify this skill did its job:

  • Every cut section had zero commands — only rationale
  • Every softened phrase was "consider / think about / you may want to / it is recommended"
  • Every added STOP: was on a hard rule that previously had no enforcement signal
  • No rule, gate, checklist item, or branching logic was removed
  • Re-running after edits returns CLEAN

Step 1: Read the skill

Read the full SKILL.md. Also read all sibling files: references/defaults.md, references/methodology-detail.md, assets/template.md, or any file referenced by a Read instruction in the skill body.

Do not edit yet — complete the full audit first.


Step 2: Apply the tighten checklist

For each item, scan the entire file. Mark every instance found — do not stop at the first.

T1 — Non-actionable sections

Sections that explain why the skill exists, describe the problem, or narrate context without issuing a single command. Cut the entire section. Preserve the pointer to a referenced file if one exists.

Patterns that always qualify:

  • Section titled "Core Principle", "Purpose", "Problem", "Background", "Why This Matters", "How It Is Used", "Integration with Other Skills"
  • Opening paragraph before a numbered list that restates what the numbered list will do
  • Closing paragraph after a gate that explains what happens if the gate were skipped

Read the full file on GitHub · 160 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 Changed 629987dbef50
  2. 8d ago First seen · 160 lines · 123 tokens per session scan A 52621eea6f11

Subscribe to this mod's changes

skill-tighten is a skill published in the GitHub repository techygarg/lattice (185 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 1,518 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

name-your-business

Generate, refine, compare, and when needed validate distinctive names for startups, AI products, developer tools, protocols, open-source projects, apps, product families, local businesses, services, companies, nonprofits, and other organizations. Use when asked to name or rename a business, brand, product, venture…

tamdogood/builder-essential-skills · 156 tokens

top-one-percent

Teach any topic deeply from first principles and build evidence-based paths toward exceptional capability. Use when a user asks to understand, explain, learn, or deep-dive into a topic; asks why or how something works, why it matters, how alternatives compare, or what different perspectives reveal; requests current…

tamdogood/builder-essential-skills · 111 tokens

paper-opportunity-radar

Run a cumulative daily or retrospective sweep of research papers on a chosen topic, audit their claims, methods, integrity signals, and independent support, then identify overlooked but feasible project or business opportunities in a detailed source-grounded report. Use when asked to monitor papers every day, mine…

tamdogood/builder-essential-skills · 98 tokens

repo-system-map

Analyze a software repository at the latest remote main commit and turn its implemented architecture into a citation-backed interactive isometric system map with a legend, selectable infrastructure buildings, dependency and payload flows, and plain-language learner explanations. For eligible public GitHub…

tamdogood/builder-essential-skills · 123 tokens

build-scenario-tests

Inspect an unfamiliar repository, turn a focused Markdown behavior scenario into a deterministic test in the repository's native test stack, run it, and preserve traceability between intent and code. Use when asked to add scenario tests, compile acceptance criteria or Given/When/Then Markdown into executable tests…

tamdogood/builder-essential-skills · 104 tokens

create-marketing-kit

Create truthful, human-centered marketing campaigns for an app or product, including positioning, channel copy, original artwork, editable layouts, README banners, and selective website integration. Use when asked to make launch materials, promotional artwork, social assets, campaign kits, ads, or marketing content…

tamdogood/builder-essential-skills · 106 tokens