Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms
The other half of the context problem. []( []( []( []( []( []( [](LICENSE) Every MCP tool call dumps raw data into your context window. A Playwright snapshot costs 56 KB. Twenty GitHub issues cost 59 KB. One access log — 45 KB. After 30 minutes, 40% of your context is gone. And when the agent compacts the conversation to free space, it forgets which files it was editing, what tasks are in…
⚠ The trust score below reflects the installer package context-mode only. The bundled units are not individually verified or scanned — review them before use.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
ctx_searchNo description publishedThis tool published no description. Forge does not invent one.
ctx_executeprivilegedNo description publishedThis tool published no description. Forge does not invent one.
ctx_execute_fileprivilegedNo description publishedThis tool published no description. Forge does not invent one.
ctx_indexNo description publishedThis tool published no description. Forge does not invent one.
ctx_fetch_and_indexNo description publishedThis tool published no description. Forge does not invent one.
ctx_batch_executeprivilegedNo description publishedThis tool published no description. Forge does not invent one.
ctx_statsNo description publishedThis tool published no description. Forge does not invent one.
ctx_doctorNo description publishedThis tool published no description. Forge does not invent one.
ctx_upgradeNo description publishedThis tool published no description. Forge does not invent one.
ctx_purgeNo description publishedThis tool published no description. Forge does not invent one.
ctx_insightNo description publishedThis tool published no description. Forge does not invent one.
context-mode.session-newNo description publishedThis tool published no description. Forge does not invent one.
context-mode.session-resetNo description publishedThis tool published no description. Forge does not invent one.
context-mode.session-stopNo description publishedThis tool published no description. Forge does not invent one.
ctx-statsNo description publishedThis tool published no description. Forge does not invent one.
ctx-doctorNo description publishedThis tool published no description. Forge does not invent one.
ctx-upgradeNo description publishedThis tool published no description. Forge does not invent one.
0 of 17 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
The other half of the context problem. []( []( []( []( []( []( [](LICENSE) Every MCP tool call dumps raw data into your context window. A Playwright snapshot costs 56 KB. Twenty GitHub issues cost 59 KB. One access log — 45 KB. After 30 minutes, 40% of your context is gone. And when the agent compacts the conversation to free space, it forgets which files it was editing, what tasks are in progress, and what you last asked for. On top of that, the agent wastes output tokens on filler,…
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This package was last scanned before Forge began storing the resolved tree. The next scan will record it.