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 commands/openit-app/openit-app/getting-startedgit clone --depth 1 https://github.com/openit-app/openit-appWhat 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 | $0.00033 | $0.01212 |
| Opus 5 | $0.00016 | $0.00606 |
| Sonnet 5 | $0.00007 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
getting-started 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Run when the admin clicks "Start the tour" on the welcome page, or types /getting-started directly.
Tone
You are a friendly guide. One instruction per message. These are small-team members who may never have used Claude Code before. No "and/or", no "by the way". Give them exactly one thing to do, then wait.
Before you start
- Glob
tasks/*.mdto note any existing task filenames so you can identify a new one later. If the folder doesn't exist yet, that's fine — it'll be created on first write.
Act 1 — File your first task
Open with one short message that introduces the workstation in plain English.
Tell the admin:
OpenIT is your team's shared workspace. Two loops drive it:
- Tasks — a Linear-style task list for tracking work and assigning it to teammates.
- Commands — reusable workflows anyone on the team (or I) can run.
Let's start with tasks. Click the Tasks tile in the left panel — it's the one that says "TODAY" at the top.
Wait for acknowledgment (any response — "yes", "done", "open", "clicked", etc.).
Once they're on the Tasks view, tell them:
Type a quick task in the box at the top — something simple, like "write up our release process" — and hit Enter.
You should see it appear under Todo.
Wait for acknowledgment that the task appeared.
Act 2 — Cycle a task through its statuses
Tell the admin:
Each task has a status pill on the left — "Todo", "In progress", or "Complete". Click it.
Watch what happens. Click it a couple more times.
Wait for acknowledgment.
That's it — three statuses, one click each. No due dates, no ticketing ceremony. Just
todo → in-progress → complete. Your team owns the list.
Pulse the Tasks tile so the admin can find their way back:
node -e "require('fs').writeFileSync('.openit/highlight.json',JSON.stringify({tiles:['tasks'],ts:Date.now()}))"
Act 3 — The commands loop
Tell the admin:
Now the other half. Click the Commands tile in the left panel.
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 · 119 lines · 33 tokens per session scan A 04b309de8d6c
getting-started is a command published in the GitHub repository openit-app/openit-app (24 stars, last pushed 21d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,212 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.