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.
git clone --depth 1 https://github.com/aegntic/cldcdeWrote 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/commands/aegntic/cldcde/capture-baseline)<a href="https://agentmods.dev/commands/aegntic/cldcde/capture-baseline"><img src="https://agentmods.dev/badge/commands/aegntic/cldcde/capture-baseline/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/commands/aegntic/cldcde/capture-baseline"><img src="https://agentmods.dev/badge/commands/aegntic/cldcde/capture-baseline.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 | $0.00000 | $0.00289 |
| Opus 5.5 | $0.00000 | $0.00116 |
| Sonnet 5.5 | $0.00000 | $0.00058 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
capture-baseline 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
/capture-baseline - Capture Visual Baseline
Capture baseline screenshots for visual regression testing.
Steps
- Identify the pages or components to capture baselines for
- Check if a visual testing tool is configured (Percy, Chromatic, reg-suit, or Playwright)
- Determine viewport sizes for captures: mobile (375px), tablet (768px), desktop (1280px)
- Start the application or Storybook server if needed
- Navigate to each target page and wait for all assets to load
- Remove dynamic content (timestamps, ads, animations) using CSS injection or masking
- Capture full-page screenshots at each viewport size
- Save screenshots to the baselines directory with descriptive naming:
{page}-{viewport}-baseline.png - Generate a manifest file listing all captured baselines with timestamps
- Report total baselines captured, file sizes, and storage location
- Commit baseline images to the repository or upload to cloud storage
Rules
- Always capture at minimum three viewport sizes (mobile, tablet, desktop)
- Wait for network idle before capturing to avoid incomplete renders
- Mask or hide dynamic content that changes between runs
- Use consistent browser and device emulation settings
- Name baselines clearly with page name and viewport size
- Store baselines in a dedicated directory separate from test code
- Compress images to keep repository size manageable
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 · 28 lines · 0 tokens per session scan A fbe2be99ab12
capture-baseline is a command published in the GitHub repository aegntic/cldcde (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 289 tokens. 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 2026-11-05.
capture-baseline compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| capture-baselineaegntic/cldcde | Command | 11 | 2d ago | MIT | A | 0 | Claude Code |
| scriptwriter-draftcambridgetcg/agenttool | Command | 0 | yesterday | Apache-2.0 | A | 35 | Claude Code |
| scriptwriter-opencambridgetcg/agenttool | Command | 0 | yesterday | Apache-2.0 | A | 47 | Claude Code |
| scriptwriter-paircambridgetcg/agenttool | Command | 0 | yesterday | Apache-2.0 | A | 38 | Claude Code |
| scriptwriter-statuscambridgetcg/agenttool | Command | 0 | yesterday | Apache-2.0 | A | 52 | Claude Code |
| scriptwriter-drawcambridgetcg/agenttool | Command | 0 | yesterday | Apache-2.0 | A | 43 | Claude Code |
| scriptwriter-initcambridgetcg/agenttool | Command | 0 | yesterday | Apache-2.0 | A | 34 | Claude Code |