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/colin-automates/codex-imagegen--claude-code/editgit clone --depth 1 https://github.com/colin-automates/Codex-ImageGen--Claude-CodeWhat 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 | $0.00026 | $0.00359 |
| Opus 5 | $0.00013 | $0.00179 |
| Sonnet 5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
edit 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.
What it actually says
The user invoked /imagegen:edit. Arguments:
$ARGUMENTS
Parse $ARGUMENTS:
- The first whitespace-separated token is
source_path. Strip surrounding quotes if present. - Everything after is the edit
prompt.
Do this without asking for confirmation:
- If
source_pathdoesn't exist on disk, tell the user that and stop. - Compute
save_path: same directory and basename assource_path, with-edited-<HHmmss>inserted before the extension. Example:hero.png→hero-edited-143012.png. - Call
mcp__plugin_imagegen_imagegen__edit_imagewith:source_path: the parsed path (resolved absolute).prompt: the edit instructions, optionally expanded with style/preservation cues from the SKILL ("preserve the overall composition", "keep the background", etc.) if the user's instruction is terse.save_path: as computed.size: match the source's aspect ratio if possible — otherwiseauto.quality:mediumby default;highif the user said "high quality" or "final".
- On success, briefly tell the user where the edited file landed.
- On failure, surface the
hintfield plus a one-sentence next step.
If the user wanted to overwrite the original instead of saving alongside, they will explicitly say so — only then set save_path = source_path.
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 · 30 lines · 26 tokens per session scan A 1f8e02116dac
edit is a command published in the GitHub repository colin-automates/Codex-ImageGen--Claude-Code (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 359 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 2026-08-31.
Other commands, from other repositories
image-generation
Generate or edit images via Codex CLI — with prompt refinement, vision validation, retry loop, and error handling.
video
🎬 GensparkでAI動画を生成する（受取人本人のアカウント）.
image
🖼️ GensparkでAI画像を生成する（受取人本人のアカウント）.
video-flow
Create a complete video animation from a description - automates the full workflow from concept to finished video.
imagine-pro
Generate an AI image with ImaginePro using best practices and intelligent guidance.
git
Git operations with intelligent commit messages and workflow optimization.