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 skills add jqaisystems/jqai-ai-skills --skill ai-image-run-pacinggit clone --depth 1 https://github.com/jqaisystems/jqai-ai-skillsWrote 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/skills/jqaisystems/jqai-ai-skills/ai-image-run-pacing)<a href="https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/ai-image-run-pacing"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/ai-image-run-pacing/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.
<a href="https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/ai-image-run-pacing"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/ai-image-run-pacing.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00078 | $0.01468 |
| Opus 5.5 | $0.00031 | $0.00587 |
| Sonnet 5.5 | $0.00016 | $0.00294 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
ai-image-run-pacing 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Image Run Pacing
Generating one image is easy. Generating a set of them in one sitting, through a hosted assistant, is where runs actually fail: throttled halfway, faces drifting between images, references silently dropped, or an agent hammering retries until the account is locked for hours.
This skill is the operating discipline for those runs. It is deliberately tool-agnostic and contains no page selectors or automation snippets, because those break the moment a provider redesigns and give a false sense of what is safe to automate.
When to use
- Generating more than two or three images in one session.
- Driving a hosted image tool with an agent, an extension, or a script.
- Recovering from "too many requests" or a temporary limit.
- Deciding how many reference images to attach, and to which turn.
- Planning a run that must finish unattended.
Credentials: the rule that has no exceptions
Never store, type, or automate an account password. Not in a config file, not in an environment variable, not passed to a browser driver.
The reason is not only leak risk. Scripted logins trip bot detection, two-factor prompts break unattended runs, and automating a login is the part most likely to put an account at risk of suspension.
The supported pattern is a persistent browser profile: open a browser window once, let the person log in by hand, and reuse that profile directory for every later run. Keep it out of version control. Deleting the directory is the logout.
If a run needs credentials to start, the design is wrong. Ask the person to log in once, and continue.
Pacing: speed is throttled, volume usually is not
The single most useful thing to know: hosted assistants generally throttle burst speed, not total volume. A run that sends ten requests in ninety seconds gets limited. The same ten requests spread across ten minutes usually do not.
- Wait 45 to 75 seconds between sends. Randomise inside that window rather than using a fixed interval. Never go below about 30 seconds.
- On a limit message, stop and wait 10 minutes. Do not retry immediately and do not reload repeatedly; both read as more load and extend the lockout.
- Light limits clear in 30 to 60 seconds. Heavy ones take 1 to 3 hours.
- Nothing is lost. Completed work stays. Make runs resumable so a rerun skips what already finished instead of regenerating it.
- Do not relaunch a run repeatedly in quick succession. Two overlapping runs is the fastest way to get limited.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 132 lines · 78 tokens per session scan A 23857df51c01
ai-image-run-pacing is a skill published in the GitHub repository jqaisystems/jqai-ai-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 78 tokens to every session and 1,468 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
reins
Drive the user's real, logged-in browser from the shell via the reins CLI. Because it's their actual browser, every site is already authenticated — so you can scrape behind logins, read cookies/tokens/localStorage, watch and replay live API traffic, call a site's own API as the signed-in user, and…
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
spring-boot-team-harness
Use when a team wants every developer's coding agent (Claude Code or Codex) to follow the same rules on a Maven Spring Boot 4 repository: setting up AGENTS.md, guardrails, shared agent settings, or build and CI checks that agents must pass before code merges. It adds ./mvnw verify gates that fail on null-safety bugs…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.