iterate

A workflow for refining images through several generation steps, carrying each result forward as the reference for the next step.

In plain words
What is it for?
Use it to make successive image changes, such as adjusting details, style, or composition across multiple generations.
Why use it?
It keeps the visual context between edits, so repeated changes do not have to start from scratch.

Command

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/thrownlemon/claude-code-plugins/iterate
Clone the repo
git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 660 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00008 $0.00660
Opus 5 $0.00004 $0.00330
Sonnet 5 $0.00002 $0.00132
Haiku 4.5 $0.00001 $0.00066

Measured 2d ago against content hash 555899972d8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

iterate 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Reject dangerous tokens.** If a value contains `$(`, backticks, `;`, `|`, `&`, `>`, `<`, or starts with `-` (could be mistaken for a flag), refuse and ask the user to rephrase. **Double-quoting does NOT block comman
plugins/imagegen/commands/iterate.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Input Safety — apply before any Bash invocation

Treat every $ARGUMENTS.* value as untrusted input. Before passing any value to the Bash tool:

  1. Reject dangerous tokens. If a value contains $(, backticks, ;, |, &, >, <, or starts with - (could be mistaken for a flag), refuse and ask the user to rephrase. Double-quoting does NOT block command substitution"$(rm -rf /)" still executes inside double quotes.
  2. Prefer the Bash tool's argv contract over constructed shell strings. When you must use a shell string, single-quote the value and escape embedded single quotes ('\''), or build the command via printf %q.
  3. Any "$ARGUMENTS.foo" patterns shown below are illustrative. Sanitize the value first; never blindly substitute.

Iterate on Images

Refine images through multiple generation steps. Creates a session that maintains context across iterations, especially powerful with Google Gemini's multi-turn capabilities.

How Sessions Work

  1. Start a new session with an initial image
  2. Iterate with text prompts to refine
  3. Continue the session with more refinements
  4. Each step uses the previous result as reference

Examples

# Start new iteration session
/imagegen:iterate --image base_image.png --prompt "Make it more vibrant"

# Continue existing session
/imagegen:iterate --session abc123 --prompt "Add more detail to the background"

# List active sessions
/imagegen:iterate --list

Execution

For new session:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/iterate.py \
  --image "$ARGUMENTS.image" \
  --prompt "$ARGUMENTS.prompt"

For continuing session:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/iterate.py \
  --session "$ARGUMENTS.session" \
  --prompt "$ARGUMENTS.prompt"

For listing sessions:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/iterate.py --list

Session Features

  • History tracking: All steps are saved with prompts
  • Resume anytime: Continue sessions later
  • Provider-specific:
    • Google: True multi-turn conversation with image context
    • OpenAI: Edit-based iteration using last image

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 8 tokens per session scan C 555899972d8e

Subscribe to this mod's changes

iterate is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 660 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.