clippos-config

clippos-config is a command for Claude Code, Codex from dylan-buck/Clippos. It costs 27 tokens per session (500 once invoked), scanned A, original, MIT.

A configuration command for the Clippos skill, which creates or processes short video clips. It sets local options such as the output folder, aspect ratios, clip count, and quality threshold.

In plain words
What is it for?
Use it to configure where clips are saved, what shapes they use, how many are made, and the minimum score they must meet.
Why use it?
It avoids repeatedly entering the same Clippos settings and checks whether the local setup is ready. It also reports whether the required Hugging Face access token and software are available.

Command for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the clippos plugin — 1 skill, 3 commands shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add dylan-buck/Clippos
Claude Code
/plugin install clippos

Made for: Claude Code, Codex.

Or install clippos, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

Wrote 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.

agentmods badge for clippos-config

README.md
[![agentmods](https://agentmods.dev/badge/commands/dylan-buck/clippos/clippos-config.svg)](https://agentmods.dev/commands/dylan-buck/clippos/clippos-config)
Your own site
<a href="https://agentmods.dev/commands/dylan-buck/clippos/clippos-config"><img src="https://agentmods.dev/badge/commands/dylan-buck/clippos/clippos-config.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00027 $0.00500
Opus 5 $0.00014 $0.00250
Sonnet 5 $0.00005 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 6d ago against content hash 8d3f9b7e8045, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

clippos-config 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 6d 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.

commands/clippos-config.md · 33 lines

What it actually says

Invoke the clippos skill's configuration workflow with the user's arguments: $ARGUMENTS

Resolve CLIPPOS_ROOT with the prologue documented in SKILL.md (env var > HERMES_SKILL_DIR > CLAUDE_PLUGIN_ROOT > ~/.hermes/skills/clippos

~/.claude/skills/clippos > ~/.codex/skills/clippos > newest plugin-cache checkout containing scripts/hermes_clippos.py > CLIPPOS_ROOT line in ~/.config/clippos/.env > $PWD). Each candidate must contain scripts/hermes_clippos.py. Run bash $CLIPPOS_ROOT/scripts/bootstrap-venv.sh; it is idempotent after a completed install and resumes incomplete .venv installs. Then resolve CLIPPOS_PYTHON to $CLIPPOS_ROOT/.venv/bin/python when executable, otherwise python3.

Run "$CLIPPOS_PYTHON" "$CLIPPOS_ROOT/scripts/clippos_skill.py" config-check first. The payload's top-level ready field reflects bins, render path, and engine extras together — anything other than true means the run will fail somewhere. If engine_imports.missing_required is non-empty, the active interpreter lacks engine extras; tell the user to either install them in that interpreter or point CLIPPOS_PYTHON at one that has them.

If the user provided defaults, write them with "$CLIPPOS_PYTHON" "$CLIPPOS_ROOT/scripts/clippos_skill.py" config-write .... For dev checkouts that lack a persisted root, also pass --root "$CLIPPOS_ROOT" once so the prologue resolves cleanly next time. If required values are missing, ask only for the missing value needed next.

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. 6d ago First seen · 33 lines · 27 tokens per session scan A 8d3f9b7e8045

Subscribe to this mod's changes

clippos-config is a command published in the GitHub repository dylan-buck/Clippos (9 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 500 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.