Pi is one of the best open coding agents out there. Minimal, fast, yours.
Now it gets what it was missing:
β Saving: large tool output folded before the model reads it. Smaller bill.
β‘ Memory: "use pnpm" on Monday, remembered on Thursday.
β’ Skills: the right skill loads when the task needs it.
No plugin. No fork. Pi already lets you set a baseUrl, so we use only that.
πππ‘ @ππππππ‘π-ππππ/πππ πππππ --πππππ ππ
Same Pi. Same model. Same key. Thank you to the Pi team at earendil-works for building it open.
Link below π
The most expensive thing in AI coding isn't the model. It's what you make it read.
β Tests. 400 pass, 1 fails. Your agent reads all 401.
β‘ Docs. You wanted one answer. It read the nav, the footer and the cookie banner.
β’ Logs. One error line, buried in 10,000.
You pay for every token. Every request, every day, every engineer.
Context Mode sits between your agent and the model. The model gets the failing test, the error, the answer. Nothing else.
Same agent. Same model. Same key. Smaller bill.
πππ‘ @ππππππ‘π-ππππ/πππ
Cheaper agents won't come from cheaper models. They'll come from smarter context.
How it works, with the numbers: contextmode.ai/docs/benchmarβ¦
Start free, 1,000 requests, no card: contextmode.ai
Context Mode solves the "too many coding agents" problem via:
β One command (less setup)
β‘ One gateway (less spend)
β’ One memory (less repeating yourself)
β is obvious. You use Claude Code, Codex, OpenCode, Pi, T3 Code, Claude Desktop and the ChatGPT app. πππ‘ @ππππππ‘π-ππππ/πππ connects all 7. No plugin, no wrapper, no fork. You keep your app, your model and your key.
β‘ is less obvious, but very powerful. Every request goes through the gateway. Large tool output is folded before the model reads it. Long sessions never compact. The right skill loads when the task needs it. Your rules on what agents may read, run and reach live in one place.
β’ is a game-changer. Tell Claude Code "we use pnpm" on Monday. On Thursday, Pi runs pnpm add in the same repo. Your agents stop starting from zero.
Your agents will keep changing. Your context shouldn't have to. Excited to build it with you all!
Link below π
A 64-character string kept 25 MB alive.
That bug, plus 3 more, killed Cloudflare Worker isolates under long coding agent sessions. One isolate death took 64 requests with it.
18 days later:
β killed requests per hour: 35.2 β 0
β hot path moved to Rust + Wasm: β55% CPU, β77% memory
β a 9-point checklist for heavy request bodies on Workers
Everything we got wrong is in the post too.
context-mode.com/blog/workerβ¦
@Cloudflare @CloudflareDev
context-mode.com/blog/workerβ¦
Context Mode retweeted
This free plugin makes Claude Code last 10x longer per session
A Playwright snapshot eats 56 KB. 20 GitHub issues eat 59 KB. One access log, 45 KB
30 minutes in and 40% of your context is GONE
Then the agent compacts and forgets which files it was editing, what tasks were open, and what you last asked for
Context Mode kills this problem completely. 31K stars on GitHub, used by teams at Google, Meta, Microsoft, NVIDIA and Stripe
What it does:
β’ Runs tool output in a sandbox. Only the result enters context. 315 KB becomes 5.4 KB. A 98% cut
β’ Saves every file edit, task, error and decision to a local SQLite database. After compaction your agent picks up exactly where it left off
β’ Makes the agent write one script instead of reading 47 files. 700 KB becomes 3.6 KB
β’ Works on 17 platforms. Claude Code, Codex, Cursor, Gemini CLI, Copilot, OpenCode and more
Setup takes 30 seconds:
/plugin marketplace add mksglu/context-mode
/plugin install context-mode@context-mode
Restart Claude Code and you're done
Longer sessions. Sharper agent. A fraction of the tokens
If you code with agents every day, install this before anything else
github.com/mksglu/context-moβ¦
Context Mode retweeted
6 GitHub repos that actually reduce Claude Code token waste:
1. Context Mode β github.com/mksglu/context-moβ¦
2. claude-mem β github.com/thedotmack/claudeβ¦
3. Caveman β github.com/JuliusBrussee/cavβ¦
4. XERJ β github.com/xerj-org/xerj
5. Claude Code MCP β github.com/anthropics/claudeβ¦
6. Orca β github.com/stablyai/orca
Bookmark this before your next long session
Context Mode retweeted
7 GitHub repos that turn Claude Code into a stronger research and writing agent:
1. Context Mode β github.com/mksglu/context-moβ¦
2. XERJ (local search for agents) β github.com/xerj-org/xerj
3. Orca (parallel agents) β github.com/stablyai/orca
4. Claude Code MCP β github.com/anthropics/claudeβ¦
5. Matt Pocockβs Skills β github.com/mattpocock/skills
6. Code Modernization β github.com/anthropics/code-mβ¦
7. Claude Code Ultimate Guide β github.com/anthropics/claudeβ¦
Bookmark this and stop researching alone
Context Mode retweeted
Replying to @contextmode
@contextmode is #3 on GitHub Trending today!
Thank you to everyone contributing code, reporting issues, and spreading the word.π«‘
Context Mode retweeted
Someone built a plugin that cuts AI coding token usage by up to 98%
Context Mode filters massive tool outputs before they reach your agent, reducing context waste while preserving searchable session memory across long coding tasks.
Setting up in Claude Code:
1. /plugin marketplace add mksglu/context-mode
2. /plugin install context-mode@context-mode
3. Restart and run /context-mode:ctx-doctor to check the hooks are live
Repo: github.com/mksglu/context-moβ¦
Every @contextmode account starts with the same default rules:
ASD-STE100, the controlled English of aircraft maintenance manuals. Plus Orwell's 6 rules from 1946.
Short answers. No wall of text. Code and terms stay exact.
Write your own once. Every agent follows them.
Context Mode retweeted
Yeah, itβs the same idea as a PreToolUse hook but it doesnβt live in the client. Protect sits on the request path, sees every call from Claude Code and Codex before it runs, strips wrappers like sudo or sh -c, and blocks based on what the call actually does. Blocked calls never reach the shell. Local hooks are easy to miss or bypass. This is one policy at the gateway for both agents on every machine. @contextmode






