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.
npx skills add ARA-Labs/Agent-Native-Research-Artifact --skill context-dropgit clone --depth 1 https://github.com/ARA-Labs/Agent-Native-Research-ArtifactWrote 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.
[](https://agentmods.dev/skills/ara-labs/agent-native-research-artifact/context-drop)<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>- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once 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 |
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.
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>`. 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.
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.
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.
- 8d ago First seen · 162 lines · 183 tokens per session scan C 828e722ddda4
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.