iterate

iterate is a command for Claude Code from luanmorenommaciel/agentspec. It costs 16 tokens per session (569 once invoked), scanned A, original, MIT.

A command for updating a planning document when requirements or technical design change during a structured development workflow. It records the change in the relevant brainstorm, requirements, or design phase.

In plain words
What is it for?
Use it to revise feature brainstorms, requirements documents, and architecture plans before rebuilding affected code.
Why use it?
It keeps written plans aligned with changing decisions and preserves a clear link between the design and later code changes.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/luanmorenommaciel/agentspec/iterate
Clone the repo
git clone --depth 1 https://github.com/luanmorenommaciel/agentspec

Made for: Claude Code.

Wrote 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.

agentmods badge for iterate

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/iterate.svg)](https://agentmods.dev/commands/luanmorenommaciel/agentspec/iterate)
Your own site
<a href="https://agentmods.dev/commands/luanmorenommaciel/agentspec/iterate"><img src="https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/iterate.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 569 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00569
Opus 5 $0.00008 $0.00284
Sonnet 5 $0.00003 $0.00114
Haiku 4.5 $0.00002 $0.00057

Measured 3d ago against content hash 69e229b6837d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

iterate 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 3d 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.

.claude/commands/workflow/iterate.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iterate Command

Update any phase document when requirements or design changes (Cross-Phase)

Usage

/iterate <file> "<change-description>"

Examples

/iterate BRAINSTORM_SEARCH_API.md "Consider ElasticSearch instead of PostgreSQL full-text search"
/iterate DEFINE_SEARCH_API.md "Add support for fuzzy matching, not just exact search"
/iterate DESIGN_SEARCH_API.md "Services need to be self-contained, no shared common/"
/iterate .claude/sdd/features/DEFINE_AUTH.md "Change from JWT to session-based auth"

What This Command Works On

/iterate updates the document phases of the SDD workflow:

Phase 0: /brainstorm → BRAINSTORM_{FEATURE}.md ← /iterate can update
Phase 1: /define     → DEFINE_{FEATURE}.md     ← /iterate can update
Phase 2: /design     → DESIGN_{FEATURE}.md     ← /iterate can update
Phase 3: /build      → (code)                  ← update DESIGN, then /build
Phase 4: /ship       → (archive)               ← N/A

Important: to change code during Phase 3, update the DESIGN document first — the cascade to code triggers a rebuild via /build. This ensures traceability.

Scope check: more than ~50% change, a different problem, or different target users is a new /define, not an iterate — the skill carries the thresholds.


What Happens

  1. Load the skill — read .claude/skills/sdd-iterate/SKILL.md; it owns the full methodology.
  2. Classify the change — additive, modifying, removing, or architectural, with impact level.
  3. Analyze cascades — walk the downstream documents (BRAINSTORM → DEFINE → DESIGN → CODE) for required updates.
  4. Confirm with the user — present the cascade options; never apply cascading edits silently.
  5. Apply — update the target (and confirmed downstream documents) with version bumps and change notes.

Output

Artifact Location
Updated document Same location as input
Cascade updates Downstream documents (if confirmed)

Read the full file on GitHub · 75 lines

Changes

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.

  1. 3d ago First seen · 75 lines · 16 tokens per session scan A 69e229b6837d

Subscribe to this mod's changes

iterate is a command published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 569 once invoked, about $0.0001 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 2026-09-01.