summarization

A tool for shortening documents, articles, conversations, code, and other technical material while keeping the important information.

In plain words
What is it for?
It creates concise summaries for purposes such as decision-making, technical reference, meeting catch-up, research review, and changelogs.
Why use it?
It helps readers understand lengthy material more quickly without having to read every detail.

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

Made for: Claude Code, Codex.

Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,820 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 $0.00144 $0.01820
Opus 5 $0.00072 $0.00910
Sonnet 5 $0.00029 $0.00364
Haiku 4.5 $0.00014 $0.00182

Measured 2d ago against content hash e6564a4735e4, 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 2d 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.

src/upsonic/skills/builtins/summarization/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Summarization

Produce concise, accurate summaries that capture what matters. A good summary saves the reader time while preserving the information they need to make decisions or take action.

Before You Summarize

Understand the context:

  1. What type of content is this? (Business doc, technical spec, conversation, research paper, code)
  2. Who is the audience? (Executive, engineer, general reader)
  3. What's the purpose? (Decision-making, catch-up, reference, sharing)
  4. How long should the summary be? (If not specified, scale to content complexity — not just length)

These determine which approach to use and what to emphasize.

Reference Materials

  • Load summary-templates.md for ready-to-use templates for each summary type (Executive, Technical, Meeting, Research, Changelog). Use these as starting structures and adapt to the specific content.

Summarization Approaches

Choose the approach that matches the content type:

Executive Summary

For business documents, reports, proposals, and strategy decks.

Structure:

  1. Bottom line first: Lead with the key decision, recommendation, or conclusion
  2. Critical metrics: Include the 2-4 numbers that matter most (revenue, timeline, cost, impact)
  3. Key findings: 3-5 bullet points covering what was discovered or decided
  4. Risks and concerns: What could go wrong, what's uncertain
  5. Next steps: Who does what by when

Example pattern:

**Recommendation:** [One sentence with the core decision]

**Key metrics:** [2-4 data points]

**Findings:**
- [Most important finding]
- [Second most important]
- [Third]

**Risks:** [1-2 key risks]

**Next steps:** [Action items with owners and deadlines]

Guidelines for executive summaries:

  • Use business language, not technical jargon
  • Every sentence should help the reader make a decision
  • If you can't state the bottom line in one sentence, the source material may be unclear — flag this
  • Include specific numbers, not vague qualifiers ("revenue grew 23%" not "revenue grew significantly")

Read the full file on GitHub · 191 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 191 lines · 144 tokens per session scan A e6564a4735e4

Subscribe to this mod's changes

summarization is a skill published in the GitHub repository Upsonic/Upsonic (7,947 stars, last pushed 2mo ago), licensed MIT. It adds 144 tokens to every session and 1,820 once invoked, about $0.0007 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

hive.browser-automation

Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…

aden-hive/hive · 142 tokens

hive.linkedin-automation

Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…

aden-hive/hive · 99 tokens

hive.worker-delegation

Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.

aden-hive/hive · 58 tokens

hive.x-automation

Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…

aden-hive/hive · 81 tokens

test-reporting

Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.

aden-hive/hive · 0 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens