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/codika-io/clave/create-workspacenpx skills add codika-io/clave --skill create-workspacegit clone --depth 1 https://github.com/codika-io/claveWhat 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 | $0.00047 | $0.08307 |
| Opus 5 | $0.00023 | $0.04154 |
| Sonnet 5 | $0.00009 | $0.01661 |
| Haiku 4.5 | $0.00005 | $0.00831 |
Grade A, and why
create-workspace 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 — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Workspace
This skill helps you create and configure .clave workspace files for the Clave desktop app — a multi-session terminal manager built on Electron.
What is a .clave file?
A .clave file is a JSON file that defines one or more groups. Each group contains sessions (terminal instances) and terminals (quick-action buttons with pre-configured commands). When dropped into Clave or loaded via the Workspaces settings, these groups become launchable templates.
Templates live in the group picker — a full-screen dialog opened from the grid icon beside the Sessions heading in the sidebar. Clicking a group stamps out a fresh one every time; it never links back to the running group. The picker shows one card per group, with a search field, and:
- Groups templates under their
categoryas section headers. Uncategorized templates render first, then categories alphabetically. There is no manual ordering — if you need a specific order, name the categories so they sort that way. - Hides groups marked
"toolbar": true(those render as icon buttons in the top toolbar instead). - Shows a search box once there are more than 5 templates.
(The old inline pinned-groups grid in the sidebar is now only a drop target for dragging groups and .clave files.)
Single-group vs multi-group
A .clave file can define either a single group or multiple groups:
Single-group (e.g. my-project.clave):
{
"$schema": "clave/1.0",
"name": "My Project",
"cwd": ".",
"color": "blue",
"sessions": [...],
"terminals": [...]
}
Multi-group / workspace (e.g. workspace.clave):
{
"$schema": "clave/1.0",
"groups": [
{ "name": "Group A", "cwd": ".", ... },
{ "name": "Group B", "cwd": "../other", ... }
]
}
The format is auto-detected: if the top level has a groups array, it's multi-group. Otherwise, it's single-group.
Path resolution
All cwd and logo paths in a .clave file are relative to a root directory, which is not always the file's own folder:
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 · 594 lines · 47 tokens per session scan A a10234fe47c4
create-workspace is a skill published in the GitHub repository codika-io/clave (47 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 8,307 once invoked, about $0.0002 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.