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 glebis/claude-skills --skill cullgit clone --depth 1 https://github.com/glebis/claude-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/glebis/claude-skills/cull)<a href="https://agentmods.dev/skills/glebis/claude-skills/cull"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/cull/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/glebis/claude-skills/cull"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/cull.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 111 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00123 | $0.01954 |
| Opus 5.5 | $0.00049 | $0.00782 |
| Sonnet 5.5 | $0.00025 | $0.00391 |
| Haiku 4.5 | $0.00012 | $0.00195 |
Grade A, and why
cull 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cull
Cull is a local AI-art image-library app: import folders, browse, rate/decide, build collections, run vision/quality analysis, find similar via embeddings, and export/publish.
Cull exposes the same operations four ways: the cull CLI, the cull:// URL scheme, the GUI, and an MCP server — all thin wrappers over one Rust core. Default to the CLI + URL scheme. They need no MCP connection and survive app restarts. Reach for the MCP only when interactive control is needed that the headless surface doesn't implement yet (see "When the MCP is needed").
The one core rule (do not skip)
To show or review images, use Cull — never open <image> or Preview. The user does not want Preview windows. Display by importing into Cull's library and fronting the app on the folder (below). Fronting the app is fine; opening image files with open is not.
Driving Cull headless (the default path)
The binary lives at /Applications/Cull.app/Contents/MacOS/cull. Set it once:
CULL="/Applications/Cull.app/Contents/MacOS/cull"
With no subcommand it launches the GUI; with a subcommand it runs headless and exits, writing to the same library DB the running app reads. Add --json for machine-readable output.
Show / review a batch — the most common task. Import (headless), then front the app on the folder via the URL scheme:
$CULL --json import_folder --folder_path "/abs/path/to/batch"
open -a /Applications/Cull.app "cull://open?path=/abs/path/to/batch&view=grid" # &view=loupe for single-image detail
open -a Cull # ensure the window is frontmost
Re-running import_folder is safe — already-imported files are skipped.
Implemented CLI subcommands
These are live in the shipped binary (cull --help to confirm). Field names match the MCP tool params.
| Command | Purpose |
|---|---|
import_folder --folder_path P / import_files --file_paths a,b |
Bring a folder / specific files into the library |
list_folders / list_images [--limit N --offset N] / list_collections |
Enumerate folders / images / collections |
get_library_stats |
Library-wide counts |
list_export_presets / export_images --image_ids … --output_dir … --format … |
List presets / export to disk (also --collection_id or --folder_path) |
get_embedding_model_download_info / download_embedding_model / generate_embeddings |
Embedding model prereq + build (async) |
analyze_image_quality / get_image_quality / get_quality_count |
Run quality analysis / read scores / count by bucket |
call_tool <tool> --params_json '{…}' |
Generic escape hatch — call any MCP-named tool with a JSON object |
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 · 112 lines · 123 tokens per session scan A 2831fedc9fd5
cull is a skill published in the GitHub repository glebis/claude-skills (400 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 1,954 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.