agentmods.dev

unpack

unpack is a skill for Claude Code from dotlas/skills. It costs 111 tokens per session (1,861 once invoked), scanned A, original, MIT.

A plain-language explainer for unfamiliar ideas, documents, code, errors, and processes. It starts from basic principles and explains how the parts fit together.

In plain words
What is it for?
Use it to understand an unfamiliar codebase or document, decode an error, summarize material, or write precise instructions for another coding agent.
Why use it?
Dense technical material often assumes background knowledge the reader does not have. This helps turn confusing descriptions or failures into a clear understanding and an actionable explanation.

Skill for Claude Code

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

Part of the custom-common plugin — 12 skills shipped together

not rated 2repo 15d ago A scan 111 tokens original MIT

Good fit Use it to understand an unfamiliar codebase or document, decode an error, summarize material, or write precise instructions for another coding agent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dotlas/skills/unpack
View source ↗ dotlas/skills skills.sh
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 dotlas/skills --skill unpack
Clone the repo
git clone --depth 1 https://github.com/dotlas/skills

Made for: Claude Code.

Or install custom-common, the plugin that ships this one along with the rest of its 12 skills.

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 unpack

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dotlas/skills/unpack"><img src="https://agentmods.dev/badge/skills/dotlas/skills/unpack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,861 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 $0.00111 $0.01861
Opus 5.5 $0.00044 $0.00744
Sonnet 5.5 $0.00022 $0.00372
Haiku 4.5 $0.00011 $0.00186

Measured 2mo ago against content hash 3a4a4bc22f06, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unpack 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 2mo 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/custom/common/unpack/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unpack — Plain, First-Principles Explanations

When To Use

Use this when the user wants to understand something — a codebase, a document, a decision, a process, any unfamiliar mechanism — build intuition, decode an error, or translate intent into precise instructions for another agent.

  • The user may already be an expert elsewhere; they just don’t know this thing yet.
  • Don’t assume the topic is technical.

Procedures

Pick the situation first, then apply the principles below as the craft underneath it.

Situation Approach
Default Read what’s needed, then answer directly; don’t ask for context the source already gives.
Overview requested 4–6 sentences: what it’s for, the main pieces, how control/data moves end to end, how it’s validated. Discover this from the source.
Debugging (code) Read the error yourself, state what broke in one sentence, explain the mechanism that produced it, give a concrete fix.
Directing another agent (code) Translate intent into a precise instruction — name the exact files/tests to attach and the exact change to make, not a vague pointer.
Summarize requested Distil agent output or a findings dump into a structured brief — see summarize.md.

Output format

  • Open with the answer — first sentence is the answer, not a windup.
  • Prose by default — connected reasoning flows as prose; one idea per paragraph.
  • Table when comparing things across shared dimensions (e.g. this vs that).
  • Bullets for genuinely parallel, non-sequential items.
  • Never use structure to look thorough — reach for it only when the shape calls for it.

Not The Same Axis As Compression

Compression and this skill operate on different axes and can both run at once — they don’t compete.

Compression mode (e.g. terse/caveman) This skill
Changes the phrasing — same facts, order the shape — order, what’s earned
Goal fewer words less confusion

Read the full file on GitHub · 176 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. 2mo ago First seen · 176 lines · 111 tokens per session scan A 3a4a4bc22f06

Subscribe to this mod's changes

unpack is a skill published in the GitHub repository dotlas/skills (2 stars, last pushed 15d ago), licensed MIT. It adds 111 tokens to every session and 1,861 once invoked, about $0.0004 per session on Opus 5.5. 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.

Claude CodeLearning and teachingWriting and docsagentic-engineeringcodexskills
Related

unpack compared with skills from other repositories

unpack next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
unpackdotlas/skillsSkill215d agoMITA111Claude Code
math-olympiadanthropics/claude-plugins-officialSkill47ktodayApache-2.0A163Claude Code
google-agents-cli-onboardinggoogle/skillsSkill24ktodayApache-2.0A95Claude Code, Codex
climbanthropics/claude-plugins-officialSkill47ktodayApache-2.0A42Claude Code
office-hoursanthropics/claude-plugins-officialSkill47ktodayApache-2.0A40Claude Code
huashu-speech-coachalchaincyf/huashu-skillsSkill2.3k2d agoMITA102Claude Code, Codex
Vibe Coding MasteryLeoYeAI/openclaw-master-skillsSkill2.2k5d agoMITA61Claude Code, Codex