summarization

summarization is a skill for Claude Code, Codex from byronxlg/skillfold. It costs 14 tokens per session (362 once invoked), scanned A, original, MIT.

A tool for shortening information while keeping its important facts, conclusions, and actions. It adjusts the amount of detail and wording for the intended audience.

In plain words
What is it for?
Use it to summarize documents, research, decisions, or task lists for readers who need either a brief overview or practical detail.
Why use it?
It removes repetition and unnecessary detail, making long material easier to understand and use.

Skill for Claude CodeCodex

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 skills/byronxlg/skillfold/summarization
Any agent
npx skills add byronxlg/skillfold --skill summarization
Clone the repo
git clone --depth 1 https://github.com/byronxlg/skillfold

Made for: Claude Code, Codex.

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 summarization

README.md
[![agentmods](https://agentmods.dev/badge/skills/byronxlg/skillfold/summarization.svg)](https://agentmods.dev/skills/byronxlg/skillfold/summarization)
Your own site
<a href="https://agentmods.dev/skills/byronxlg/skillfold/summarization"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/summarization.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 362 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 $0.00014 $0.00362
Opus 5 $0.00007 $0.00181
Sonnet 5 $0.00003 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 5d ago against content hash 1d8d885ba68f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

summarization 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 5d 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.

library/skills/summarization/SKILL.md · 39 lines

What it actually says

Summarization

You condense information into clear, accurate summaries. You preserve what matters and cut what does not, adjusting detail level to the audience and purpose.

Principles

  • A summary must be accurate - never introduce claims that are not in the source material
  • Preserve the key points, conclusions, and actionable items
  • Cut supporting detail, repetition, and tangential information
  • Adjust length and detail to the audience: executives need conclusions, practitioners need specifics
  • Maintain the original tone and intent - do not editorialize

Approach

When summarizing:

  1. Read the full source material before starting - understand the whole picture first
  2. Identify the main points: What are the key facts, decisions, or conclusions?
  3. Identify what is actionable: Are there tasks, deadlines, or decisions that require follow-up?
  4. Draft the summary at the requested detail level
  5. Verify that every claim in the summary is supported by the source material
  6. Check that no critical information was lost - would someone acting on this summary make the same decisions as someone who read the full text?

Detail Levels

  • One-line: The single most important takeaway
  • Brief (1-3 sentences): Key conclusion plus the most important supporting point
  • Standard (1-2 paragraphs): All major points with enough context to understand them
  • Detailed: All significant points with supporting evidence, organized by topic

Output

Produce a summary at the requested detail level. Lead with the most important information. Use structure (bullets, sections) when it improves scanability. If the source material contains action items or decisions, highlight them separately.

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. 5d ago First seen · 39 lines · 14 tokens per session scan A 1d8d885ba68f

Subscribe to this mod's changes

summarization is a skill published in the GitHub repository byronxlg/skillfold (12 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 362 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 2026-08-30.

Related

Other skills, from other repositories

audit-onboarding-proposal

Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…

hoangnb24/repository-harness · 104 tokens

engineering-wisdom

Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…

hoangnb24/repository-harness · 78 tokens

proxmox-full

Complete Proxmox VE hypervisor management via REST API - VMs, containers, snapshots, backups, storage.

marcusquinn/aidevops · 27 tokens

red-team-adversarial

Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.

KbWen/agentic-os · 50 tokens

marketing-copy

Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be…

scarletkc/agents · 121 tokens

verification-before-completion

Enforce "no evidence = no completion"; run Gate Function verification before declaring done.

KbWen/agentic-os · 22 tokens