peon-ping
Plays game character voice lines and shows on-screen banners when your AI coding agent finishes or needs permission, so you can tab away without missing it. Works across many coding agents and IDEs.
7 skills5.1k
@peonpingHooks
Plugin
contexere
The one place for the skills, keys and memory of every agent you use. Formerly OMNI.
Plugin Signal67/100Solid
maintained100
capable14
documented100
adopted55
Claude Code
> /plugin marketplace add fajarhide/contexere> /plugin install contexere@omni
Codex
$ npx skills add fajarhide/contexere -a codex
Cursor
$ npx skills add fajarhide/contexere -a cursor
Gemini CLI
$ npx skills add fajarhide/contexere -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add fajarhide/contexere$ copilot plugin install contexere@omni
OpenCode
$ npx skills add fajarhide/contexere -a opencode
Windsurf
$ npx skills add fajarhide/contexere -a windsurf
Stats
377
Stars
36
Forks
Active
Maintenance
Rust
Language
Apache-2.0
License
Last commit
Created
Added
What's inside
README
Your AI agent, the same in every environment: its workflow, tools and access come with it, and its keys never reach it. That is where it is going. Today it shrinks noisy tool output, folds what an agent already read, and redacts credentials in the output it rewrites. Nothing is lost.
🇺🇸 English | 🇯🇵 日本語 | 🇨🇳 简体中文 | 🇸🇦 العربية | 🇮🇩 Bahasa Indonesia | 🇻🇳 Tiếng Việt | 🇰🇷 한국어
brew install fajarhide/tap/contexere && contexere init
OMNI is now Contexere, Latin for "to weave together" and the root of "context". The
omnicommand keeps working until 0.9.0; runcontexere init --<host>for each agent you use to move an existing install across. Since 0.8.6 your data moves to~/.contexereon its own.
Where it is going
The goal: take Contexere to a new VPS or laptop, and your agent arrives knowing its workflow, with its access to MCP servers and APIs working. The keys behind that access are never shown to the agent, so they never leak. Around that sit skills you set up once for every agent, and memory that carries across agents and machines. That part is on the way. What ships today is the first piece, the context and token layer described below.
Why
A coding agent reads everything a command prints: progress bars, layer hashes, a file it already read ten minutes ago. Every byte is billed and takes room the agent needs for the actual work.
Contexere takes out what the model does not need, before the model reads it. Nothing is deleted: whatever it removes stays on your machine, and one command brings it back.
Features
- Reads a file the agent already read: sends one line with a handle instead of the file again.
- Runs a noisy build or test: keeps the result and the failures, drops the progress noise.
- Prints a token or password in output it rewrites: replaces it with
[REDACTED]before the model sees it. - Fails a command: passes it through as printed, so the real error reaches the agent. A credential printed by a failing command reaches the agent too.
- Reads JSON, YAML or CSV: leaves it byte for byte.
contexere doctorchecks that each agent's hooks fire and redact.
It costs about 21 ms per command. Savings depend on what your agent does; run contexere stats for your own figure. Method and full numbers are on the benchmarks page.
Install
brew install fajarhide/tap/contexere
| Where | Command |
|---|---|
| macOS, Linux, WSL | curl -fsSL omni.weekndlabs.com/install | bash |
| Windows (PowerShell) | irm omni.weekndlabs.com/install.ps1 | iex |
Existing installs keep working under omni, the same program, until 0.9.0. Run contexere init --<host> for each agent to move them across (what changes).
Inside Claude Code, /plugin marketplace add fajarhide/contexere then /plugin install contexere@omni adds a skill that installs and checks it for you.
Usage
contexere init # pick your agents: Claude Code, Codex, Cursor, VS Code and more
contexere doctor # check it is wired, or `contexere doctor --fix`
contexere stats # what Contexere saved on your own history
After init, the hooks run on their own. There is nothing to prefix.
Supported agents
| Tier | Agents |
|---|---|
| Full (rewrites tool output before the model reads it) | Claude Code, Codex CLI, Gemini CLI, OpenClaw, Hermes, Pi, Aider (via cmd | contexere) |
Handoff-first (shortens what the agent runs through contexere_run) | Cursor, Windsurf |
MCP-only (memory and recall, plus contexere_run) | Cline, Roo, OpenCode, VS Code, Zed, Copilot, Antigravity |
Codex runs only hooks it trusts: after contexere init --codex, start codex once and approve them (#359).
Documentation
Contributing
Issues and pull requests are welcome. Start with CONTRIBUTING.md.
Security
Do not open a public issue. Report privately; details in SECURITY.md.
License
Stars on GitHub
Momentum
- stars in total
- 377
File tree
Similar plugins.
@peonpingstop-that-shit
Hooks and skills that stop an AI coding agent from adding unrequested hashes, checksums, or extra scope to a task. Built for Codex and GPT workflows across several platforms.
2 skills8 hooks3.9k
@lennneyprompt-improver
Enriches vague prompts for Claude Code with targeted research and clarifying questions before execution. It injects relevant context at prompt submit, tool use, and subagent start so Claude has what it needs before acting.
1 skill3 hooks2k
@severity1probity
Probity forces AI coding agents to follow your rules. It hooks into your agent and checks every file write and shell command before it happens. When an action breaks a rule, Probity blocks it and tells the agent why.
1 hook245
@nizosQuestions about contexere.
The one place for the skills, keys and memory of every agent you use. Formerly OMNI. Install it with the command on its page. It includes contexere. Its skills do not fire on their own yet. Free and open source.
- What is contexere?
- The one place for the skills, keys and memory of every agent you use. Formerly OMNI.
- How do I install contexere?
- Run these in Claude Code: /plugin marketplace add fajarhide/contexere then /plugin install contexere@omni. Then prompt normally.
- Does contexere auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin.
- Is contexere free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
- Which coding agents can use contexere's skills?
- contexere installs in Claude Code, and its skills also install in Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI. Each skill's page has the install command. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it