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/phase-2-step-3git clone --depth 1 https://github.com/Arsxxi/iterative-dev-workflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/arsxxi/iterative-dev-workflow/phase-2-step-3)<a href="https://agentmods.dev/commands/arsxxi/iterative-dev-workflow/phase-2-step-3"><img src="https://agentmods.dev/badge/commands/arsxxi/iterative-dev-workflow/phase-2-step-3.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00009 | $0.01013 |
| Opus 5 | $0.00005 | $0.00507 |
| Sonnet 5 | $0.00002 | $0.00203 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
phase-2-step-3 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 4d 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 — 92 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: project name
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 — find which project this is for
Before anything else, figure out which project this command applies to:
- If you were given a project name after the slash (e.g.
/phase-2-step-3 my-project), use it. - Otherwise, look at the subfolders under
.workflow/:- Exactly one folder → use it. Tell the user which project you picked (e.g. "Working on
my-project"), so it's never a silent guess. - Two or more folders → ask the user once which project this is for. To make the question
useful, show the first line of each project's
00-context.md, not just the folder name. - No folders → stop and tell the user to run
/kickofffirst. Don't proceed.
- Exactly one folder → use it. Tell the user which project you picked (e.g. "Working on
Phase 2 Step 3: Quality Attribute
Purpose
Assess the results from Step 2: ATAM using Weighted Scoring Assessment, against Quality Attributes designed specifically for this project.
Steps
-
Check for the previous result from Step 2 (ATAM). If it's empty or not generated, DO NOT PROCEED TO EXECUTE THIS STEP — remind the user.
-
Ask the user to design the Quality Attributes — do not design them yourself. Present this to the user:
You will need to design these Quality Attributes by yourself and assign each Attribute a Score Range. Base this design on the problem you need to solve, the project requirements, or any other relatable requirements (FR, NFR). The example below shows a project that takes Performance as the highest-priority Quality Attribute, and therefore gives Performance the highest score (0-4) range.
These are example only. YOU MUST DESIGN YOUR OWN QUALITY ATTRIBUTE TO FIT THE PROJECT REQUIREMENTS. The example below is specifically tailored for the MP project.
Example of Quality Attribute (reference format only — Quality Attribute to assess UI system design). These quality attributes have priority from highest in 1 to lowest in 4. The main goal is not to pick the design that satisfies only one quality attribute, but the design that scores great in all of these quality attributes — the scoring system will be different in each quality attribute (highest - lowest):
- Developer Experience (0-4): ease of use for multiple range of developers (junior, senior, non-react, react, etc.)
- Maintainability (0-3): clean code structure, etc.
- Reliability (0-2): system reliable in multiple platform (ios, android), etc.
- Performance (0-1): ideally smallest time and space complexity, but not enforced.
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.
- 4d ago First seen · 92 lines · 9 tokens per session scan A fd85a9f60c5f
phase-2-step-3 is a command published in the GitHub repository Arsxxi/iterative-dev-workflow (2 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,013 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
notebook
Local NotebookLM over a FOLDER of documents using Antigravity (agy). Sweeps each document (PDF with text, scanned PDF, image, docx) into an objective-driven Markdown summary, then builds a relevance INDEX and a cited master summary. Incremental cache (re-runs only re-summarize changed docs / changed objective) and…
deep-research
Deep, multi-source, fact-checked web research with agy — reach for it when a decision or design depends on getting it right and a single-shot answer is not enough (architecture / tool / vendor choices, thorough landscape scans, anything you will act on). Builds an evidence matrix + a plan you approve, then agy browses…
report
Generate a publication-grade HTML report from a markdown source using the TRAID Design System catalog (5 templates). Agy matches content to template, you confirm, agy produces final branded HTML.
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…
graph
Build a knowledge GRAPH of a folder (code + docs) with Graphify — tree-sitter ASTs + NetworkX + Leiden communities + an interactive graph.html. The code graph is built LOCALLY and costs zero tokens on any assistant; Gemini via agy only names the communities. Then Claude reads graph.json / GRAPHREPORT.md to reason…
model
Show or set the agy (Antigravity / Gemini) model by writing /.gemini/antigravity-cli/settings.json — the reliable way to switch models (the unreliable --model flag silently falls back to the default). No agy call; takes effect immediately, no plugin reinstall.