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/carta/plugins/homenpx skills add carta/plugins --skill homegit clone --depth 1 https://github.com/carta/pluginsWhat 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 | $0.00105 | $0.01546 |
| Opus 5 | $0.00053 | $0.00773 |
| Sonnet 5 | $0.00021 | $0.00309 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
home 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carta CRM Home
The Home is one manifest tool plus one view. The server decides which cards this organization may see, and the view fetches each card itself. Your job is to read the manifest, route a new user to the tutorial, and render the view.
Step 1 — Read the manifest
Call it for data first, not for the view:
crm_call_tool({ "name": "crm:get_crm_home", "arguments": {} })
Read it for data before you render anything. Step 2 can send the user elsewhere, and a Home that renders and is then retracted is worse than one that never rendered.
If the tool does not exist
The Home is behind a rollout flag. When it is off the server does not register
get_crm_home at all, and the call fails with an unknown-tool error. That is a normal
answer for an organization outside the rollout, not a failure.
What you do next depends on what the user asked for.
| The user asked for | Do this |
|---|---|
The Home itself, a dashboard, or /home |
Say the Home is not switched on for their organization, and offer what they can ask for instead |
| Something a card would have shown, such as "what's in my pipeline today" | Answer the question through the skill that owns it, here search-deals. Do not mention the Home |
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 · 133 lines · 105 tokens per session scan A 43d596e5cf77
home is a skill published in the GitHub repository carta/plugins (12 stars, last pushed today), licensed Apache-2.0. It adds 105 tokens to every session and 1,546 once invoked, about $0.0005 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
release
Release a new version of the DevoxxGenie IntelliJ plugin — prompt for the target version, bump it in the build files, write a curated CHANGELOG.md entry and plugin.xml change-notes from the git/PR history since the last tag, build to verify, then commit, tag, and publish a matching GitHub release. Use this whenever…
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
git-commit-push-pr
Commit all changes, push to remote, and open a pull request in one go. Use when the user says "commit push pr", "ship it", "open a pr", or invokes /git-commit-push-pr.
start-task
Create a feature branch for a backlog task, switch to it, and start implementation. Use when the user says "start task-123", "work on task-123", "implement task-123", or invokes /start-task with a task ID.
review
Review local code changes for bugs, regressions, missing tests, and pragmatic improvements. Use when the user asks to review the current changes from git status, or to review a specific backlog task by id such as task-65 or TASK-65. Also trigger when the user says things like "review", "review current changes", "check…
pr
DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development with CLI Runners.