summarize

summarize is a skill for Claude Code, Codex from surfmind-space/awesome-surfmind. It costs 77 tokens per session (761 once invoked), scanned A, original, MIT.

A tool that turns an article, email thread, chat, PDF, document, image, or transcript into a concise summary of its main points and decisions.

In plain words
What is it for?
Use it for quick overviews, meeting or chat recaps, document summaries, and lists of decisions, open questions, or next steps.
Why use it?
It saves you from reading everything when you need the essential information quickly. It also avoids filling in details that are missing from the source.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/surfmind-space/awesome-surfmind/summarize
Any agent
npx skills add surfmind-space/awesome-surfmind --skill summarize
Clone the repo
git clone --depth 1 https://github.com/surfmind-space/awesome-surfmind

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 summarize

README.md
[![agentmods](https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/summarize.svg)](https://agentmods.dev/skills/surfmind-space/awesome-surfmind/summarize)
Your own site
<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/summarize"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/summarize.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 761 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 5.1 $0.00077 $0.00761
Opus 5 $0.00039 $0.00380
Sonnet 5 $0.00015 $0.00152
Haiku 4.5 $0.00008 $0.00076

Measured 6d ago against content hash 21f5e38f755b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

summarize 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 6d 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/summarize/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Summarize

Produce a summary that fits the source. There is no single template: first pick the source, then detect what kind of content it is and shape the summary to match.

1. Choose the source

Priority order: selected text, then an attached file, PDF, or image, then the visible page content. Summarize only what is actually present. Never invent details, quotes, numbers, names, dates, or outcomes that are not in the source. If the context is incomplete or truncated, summarize what is available and note the gap.

2. Adapt to the content type

Content type Capture Shape the output as
Article / blog / web page Thesis, main arguments, supporting evidence, conclusion One-line TL;DR + three to six bullets
Documentation / reference What it's for, key steps or APIs, caveats Short bullets grouped by topic
Email thread Participants, the ask, decisions, open questions, action items + owners "Bottom line" line, then Decisions / Open questions / Action items
Chat / messaging conversation Who's talking, the topic, what was agreed, next steps Topic-grouped bullets; keep the resolution explicit
PDF / long document / report Purpose, section findings, recommendations Headed sections or nested bullets
Spreadsheet / data / table What it measures, notable totals, outliers, trends Bullets, keeping key figures exact
Image / screenshot / chart What it depicts, labels, the takeaway it conveys One to three sentences; describe only what is visible
Transcript (video / call / podcast) Topic, key points per speaker or segment, conclusions, action items Bullets, optionally timestamped
Code / PR / diff What it does, notable changes, risks Bullets by change

Read the full file on GitHub · 58 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. 6d ago First seen · 58 lines · 77 tokens per session scan A 21f5e38f755b

Subscribe to this mod's changes

summarize is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 761 once invoked, about $0.0004 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.