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 agentmods add skills/ziplyne-agency/codegrid/using-codegridnpx skills add ZipLyne-Agency/CodeGrid --skill using-codegridgit clone --depth 1 https://github.com/ZipLyne-Agency/CodeGridWhat 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 | $0.00127 | $0.02476 |
| Opus 5 | $0.00063 | $0.01238 |
| Sonnet 5 | $0.00025 | $0.00495 |
| Haiku 4.5 | $0.00013 | $0.00248 |
Grade A, and why
using-codegrid scanned grade A with 0 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating CodeGrid
CodeGrid is a native macOS workspace where several coding agents run side by
side, each in its own pane on an infinite 2D canvas. It is local-first:
no cloud, no account, no stored API keys. Agents are launched as normal CLIs
(claude, codex, gemini, cursor-agent, grok, or a shell) — CodeGrid does
not wrap or replace them, so they behave exactly as they do in a terminal.
This skill is your operating manual for driving CodeGrid — discovering what is running, reading and messaging other panes, and opening projects — both from inside a pane (via MCP tools) and from outside (via the local control socket or deep links).
1. Orientation: how to tell you're in CodeGrid
You are very likely running inside CodeGrid if any of these hold:
- The MCP server
codegrid-agent-busis connected (run/mcpto check). Its tools —list_agents,read_pane,message_agent— are the primary way you interact with sibling agents. - The control socket exists:
~/.codegrid/socket(its path is also written to~/.codegrid/socket-path). - You were started with a working directory chosen in CodeGrid's new-session dialog.
If the codegrid-agent-bus tools are not present but the user wants
collaboration, tell them to enable it (onboarding → "Enable collaboration", or
run node <app>/Contents/Resources/resources/agent-bus-mcp.cjs setup) and then
open a fresh pane — tools load at pane start.
2. The mental model
| Term | Meaning |
|---|---|
| Canvas | An infinite 2D surface holding panes. Each workspace has its own. |
| Pane / Session | One running process (an agent or shell) with a working dir, git branch, live terminal, and a stable session_id. The pane is its window. |
| Agent | The CLI inside a session: claude, codex, gemini, cursor, grok, or a shell. |
| Workspace | A named project context — its own panes, layout, and (optionally) bound repo. |
| Agent Bus | The local channel that lets one agent read/message another's pane. |
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.
- 2d ago First seen · 214 lines · 127 tokens per session scan A 920695012ef9
using-codegrid is a skill published in the GitHub repository ZipLyne-Agency/CodeGrid (23 stars, last pushed 20d ago), licensed MIT. It adds 127 tokens to every session and 2,476 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
gui-onboarding-verification-skill
GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
gui-integration-test
GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…
gui-settings-ui
GUI desktop app only. How to build a Settings page in the Warp client (app/src/settingsview) so its widgets and settings search behave correctly — picking a PageType, deciding whether a heading belongs in the page-title slot or inside a widget, gating a widget, and scoping searchterms per widget. Use when adding or…
logging-and-error-reporting
How and when to log (log:: levels, safe macros) and report errors to Sentry (reporterror!) in the Warp codebase. Use when adding or reviewing any logging or error reporting — picking a log level, deciding log vs. reporterror!, keeping sensitive data out of logs, or surfacing an error to Sentry.