What is speckit-iterate-define?

An iteration-planning tool that compares a requested change with the current feature specification and implementation progress. It writes a reviewable plan to pending-iteration.md without changing the existing specification files.

Use it when an existing feature needs additions, changes, removals, or a new phase.

It turns a change request into a concrete plan while protecting the current feature documents from unreviewed edits. It also checks that the feature branch has the required Spec Kit context.

speckit-iterate-define — Skill for Claude Code by opsmill

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.

Any agent

npx skills add opsmill/infrahub-mcp --skill speckit-iterate-define

Clone the repo

git clone --depth 1 https://github.com/opsmill/infrahub-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/opsmill/infrahub-mcp/speckit-iterate-define/github.svg)](https://agentmods.dev/skills/opsmill/infrahub-mcp/speckit-iterate-define)

Your own site

<a href="https://agentmods.dev/skills/opsmill/infrahub-mcp/speckit-iterate-define"><img src="https://agentmods.dev/badge/skills/opsmill/infrahub-mcp/speckit-iterate-define/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/opsmill/infrahub-mcp/speckit-iterate-define"><img src="https://agentmods.dev/badge/skills/opsmill/infrahub-mcp/speckit-iterate-define.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,319 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.02319
Opus 5	$0.00018	$0.01159
Sonnet 5	$0.00007	$0.00464
Haiku 4.5	$0.00004	$0.00232

Measured 9d ago against content hash 02c0c624ef59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

speckit-iterate-define scanned grade C with 1 finding 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 9d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

- **Preserve completed work by default** — flag risks when completed tasks are affected, but don't refuse the iteration. The user decides.

.agents/skills/speckit-iterate-define/SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

The text the user typed after /speckit.iterate.define is the change request. It describes what should be added, modified, or removed from the current feature — either the whole feature or a specific phase/subtask.

Outline

Goal: Analyze a requested change against the feature's current spec state and implementation progress, then produce a reviewable iteration plan written to pending-iteration.md. This command does not modify any spec artifacts — it only writes the pending iteration file.

1. Initialize Feature Context

Run .specify/scripts/bash/check-prerequisites.sh --json --paths-only from repo root once. Parse JSON payload fields:

FEATURE_DIR
FEATURE_SPEC
(Optionally capture IMPL_PLAN, TASKS for downstream use.)

If JSON parsing fails, abort and instruct the user to run /speckit.specify or verify the feature branch environment.

For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").

2. Check for Existing Pending Iteration

Check if FEATURE_DIR/pending-iteration.md already exists. If it does:

Warn the user: "A pending iteration already exists. Running define again will overwrite it."
Show the existing file's change_request and created date from its frontmatter.
Ask the user to confirm before proceeding, or suggest running /speckit.iterate.apply first.

3. Load Current Artifacts

Read all available artifacts from FEATURE_DIR:

REQUIRED: spec.md — requirements, user stories, edge cases, scope
IF EXISTS: plan.md — tech stack, architecture, file structure, phases
IF EXISTS: tasks.md — task list with IDs, phases, checkboxes, dependencies
IF EXISTS: data-model.md — entities, attributes, relationships
IF EXISTS: research.md — technical decisions and constraints
IF EXISTS: quickstart.md — integration/test scenarios
IF EXISTS: checklists/ — quality checklists

Read the full file on GitHub · 261 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.

9d ago First seen · 261 lines · 36 tokens per session scan C 02c0c624ef59

Subscribe to this mod's changes

speckit-iterate-define is a skill published in the GitHub repository opsmill/infrahub-mcp (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 2,319 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

LLM Planning agent ai coding-agent infrahub infrastructure

lambda-gpu-cloud

Safely inspect and operate Lambda Cloud GPU instances through the documented Cloud API and SSH, with explicit approval before billable or destructive actions.

synthetic-sciences/openscience · 32 tokens

runpod-gpu-cloud

Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.

synthetic-sciences/openscience · 32 tokens

tensorpool-gpu-cloud

Safely inspect and operate TensorPool GPU clusters and jobs using the current tp CLI, with explicit approval before any billable or destructive action.

synthetic-sciences/openscience · 34 tokens

vast-ai-gpu-cloud

Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.