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/arsxxi/iterative-dev-workflow/kickoffgit clone --depth 1 https://github.com/Arsxxi/iterative-dev-workflowWhat 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 | $0.00002 | $0.01178 |
| Opus 5 | $0.00001 | $0.00589 |
| Sonnet 5 | $0.00000 | $0.00236 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
kickoff 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
Kilo Code does not substitute $ARGUMENTS. Wherever this command refers to
$ARGUMENTS, read it as the text I typed after the slash command in this message.
Expected: optional: project name and what we're building
If I typed nothing after the command, do not guess and do not invent a value: ask me
for it with the question tool, then continue from there.
Step 0 - figure out what we're building (do this FIRST, before anything else)
Look at what was passed in: $ARGUMENTS
-
If it already clearly states a project name, a real description of what to build, AND the platform/stack (e.g. "React Native non-Expo", "Python backend service", "LLM agent pipeline"), confirm your understanding back to me in one or two sentences and proceed to the section below.
-
If any of those three are missing or vague, stop and ask me:
- What are we building? (be as comprehensive as you want me to be - the more detail, the better Phase 1 will be)
- What platform/stack is this for? (e.g. mobile app - React Native/Expo/native, backend service, LLM/agent pipeline, web frontend, CLI tool, etc. - this changes what Phase 1's library/service analysis actually looks like)
- What short project name should identify it? (used for the
.workflow/<slug>/folder, e.g.article-quality-widget)
Do not guess or invent a feature, and do not assume a default platform/stack (do not assume React Native or anything else) to analyze. Do not proceed past this point until I've answered.
Also ask (can be part of the same question round): what services/infra already exist in this project that Phase 1 should treat as "Existing Services" (e.g. a specific backend, database, auth provider, third-party APIs already wired up) - versus what's clearly new and would count as "Proposed Services". If I say I'm not sure or there's nothing existing yet, that's a valid answer - don't invent a services list.
Once you know the platform/stack and existing services, use them consistently for the rest of this workflow (Phase 1's library/package questions, Phase 2's architecture diagrams, etc. should all be framed for this specific project, not a generic or assumed one).
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 · 102 lines · 2 tokens per session scan A 2548518f1ba6
kickoff is a command published in the GitHub repository Arsxxi/iterative-dev-workflow (2 stars, last pushed 1mo ago), licensed MIT. It adds 2 tokens to every session and 1,178 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
spec
Start spec-driven development — write a structured specification before writing code.
toh-help
Display all Toh Framework commands and quick usage guide.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
notebook-status
Check the progress of a /agy:notebook sweep (for long document sets run with --background). Reports % complete, done/pending/failed counts, elapsed time and a rough ETA, and which documents are still pending — so you can resume. Read-only, no agy.
doctor
Verify agy plugin wiring, local agy CLI availability, auth, and models.
models
List models available to the local Antigravity (agy) CLI.