context-drop

context-drop is a skill for Claude Code from ARA-Labs/Agent-Native-Research-Artifact. It costs 183 tokens per session (1,772 once invoked), scanned C, original, MIT.

A way to package files and notes into one shareable link for another coding agent. The receiving agent gets the original text and links to binary files such as PDFs, spreadsheets, or images.

In plain words
What is it for?
Use it to share a file, folder, or set of notes with someone else's agent and give that agent a ready-to-paste link and prompt.
Why use it?
It avoids sending a temporary repository or archive and reduces the risk of losing important context through summarising or manual copying.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable.

Good fit Use it to share a file, folder, or set of notes with someone else's agent and give that agent a ready-to-paste link and prompt.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ara-labs/agent-native-research-artifact/context-drop
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 ARA-Labs/Agent-Native-Research-Artifact --skill context-drop
Clone the repo
git clone --depth 1 https://github.com/ARA-Labs/Agent-Native-Research-Artifact

Made for: Claude Code.

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 context-drop

README.md
[![agentmods](https://agentmods.dev/badge/skills/ara-labs/agent-native-research-artifact/context-drop.svg)](https://agentmods.dev/skills/ara-labs/agent-native-research-artifact/context-drop)
Your own site
<a href="https://agentmods.dev/skills/ara-labs/agent-native-research-artifact/context-drop"><img src="https://agentmods.dev/badge/skills/ara-labs/agent-native-research-artifact/context-drop.svg" alt="Measured on agentmods" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,772 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Supply Chain · line 75
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 $0.00183 $0.01772
Opus 5 $0.00092 $0.00886
Sonnet 5 $0.00037 $0.00354
Haiku 4.5 $0.00018 $0.00177

Measured 8d ago against content hash 828e722ddda4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

context-drop scanned grade C with 2 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/drop.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

`curl -fsSL https://www.agenticresearch.sh/s/drop.py | python3 - <path>`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -fsSL https://www.agenticresearch.sh/s/drop.py | python3 - <path>`.
skills/context-drop/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Drop

Somebody else's agent needs to read files that live on your machine. Today that means pushing a throwaway repo to GitHub, or mailing a zip the recipient has to unpack before their agent can see any of it. A context drop is the short way: upload the path, get a URL and a prompt, paste the prompt into whatever chat you were already in.

Two halves. Sending turns a path into a link. Receiving turns a link into context.


Fidelity — a drop is the material, not an account of it

Never summarize, abridge, excerpt, or paraphrase what goes into a drop. The recipient's agent reasons from this and cannot ask what was left out, so a drop that lost something is worse than no drop: it reads as complete. Summarize only when the user asks for a summary in those words — "share this with X" is not that request, and neither is a long file.

Two places where content leaks out without anyone noticing.

Container formats. A .docx, .pptx, .xlsx, .pdf, .ipynb, or .zip is a bundle wearing one file's name. Regex-stripping the tags out of word/document.xml looks like it worked while silently flattening every table's column structure and dropping every embedded image. Unpack properly: convert to Markdown in document order with tables rendered as tables, write each embedded media file out beside it under a name that says what it is, and keep the original file in the drop so the recipient can return to the source. Then read the conversion against the original and confirm nothing vanished.

Figures that carry text. A diagram is frequently where the real numbers live, and the surrounding prose may never repeat them. An image in a drop is fetchable, but only by a recipient who can see it. Transcribe every such figure verbatim into the Markdown at the point where it appears, preserving the panel layout, and mark it as a transcription so it is not mistaken for the sender's own prose. Ship the image as well.

Whenever anything was converted, say so in --note and in a comment at the top of the converted file: what the source was, what the conversion preserved, and that nothing was summarized.

Read the full file on GitHub · 162 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. 8d ago First seen · 162 lines · 183 tokens per session scan C 828e722ddda4

Subscribe to this mod's changes

context-drop is a skill published in the GitHub repository ARA-Labs/Agent-Native-Research-Artifact (676 stars, last pushed 14d ago), licensed MIT. It adds 183 tokens to every session and 1,772 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.