A new mcp tool called context-mode claims a 98 percent token reduction for coding agents across 17…
a new mcp tool called context-mode claims a 98 percent token reduction for coding agents across 17 platforms by sandboxing tool output before it enters the window. the bottleneck in agent coding is no longer the model, it is how much context you can afford.
the cheapest optimization is deleting what the agent never needed.
Context
The context-mode repository by mksglu says it sandboxes tool output (98% reduction), persists session memory and enforces routing across 17 platforms via MCP and hooks, with a worked example where 315 KB becomes 5.4 KB. The repository carries an ELv2 (Elastic License 2.0) license badge and showed 20,331 stars as fetched.
The 98% and the 17 platforms are the maker's own claims. The 98% is a single worked example of tool output, not a measured average across tasks or platforms, and no independent benchmark was read. It reduces tool-output tokens entering context, not total agent token use. New is not supported, since the maker's blog dates to 26 February 2026. Elastic License 2.0 is source-available, not open source in the OSI sense.
Related work
- context-mode blog (26 Feb 2026) ↗Snippet only.
Watch next
- An independent benchmark.
Sources
- mksglu/context-mode (GitHub)github.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 16:35 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →