agentmods.dev

codex-cli

Setup and configuration instructions for connecting the watch-skill video tool to Codex CLI, the command-line version of OpenAI Codex. The guide includes installation, configuration, and a basic test.

In plain words
What is it for?
Use it to configure video watching in Codex CLI, confirm the server with the MCP command, and ask questions about online videos.
Why use it?
It shows the exact Codex CLI settings needed to add the video tool and how to check that it is connected before using it.

Agent

320 yesterday B scan 0 tokens original MIT
View the source file oxbshw/watch-skill
Install

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.

agentmods
npx agentmods add agents/oxbshw/watch-skill/codex-cli
Clone the repo
git clone --depth 1 https://github.com/oxbshw/watch-skill
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.00488
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured yesterday against content hash 37f6a06e435a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-cli scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add to `~/.codex/config.toml`:
docs/agents/codex-cli.md · 57 lines

What it actually says

Watch Skill in Codex CLI (OpenAI)

Status: machine-configured ◐ — config written by watch-skill setup on a real machine; codex mcp list shows watch-skill enabled and the server command answers MCP initialize. A full codex chat session was not run.

Install

uvx --from "watch-skill[standard]" watch-skill doctor

uvx fetches the package on first use and needs no checkout. Prefer a permanent install? pipx install "watch-skill[standard]", then use "command": "watch-skill", "args": ["serve"] in the config below.

git clone https://github.com/oxbshw/watch-skill && cd watch-skill
uv sync --extra all
uv run watch-skill doctor

Then run watch-skill setup, which writes the config pointing at your checkout rather than the published package.

Configure

Add to ~/.codex/config.toml:

[mcp_servers.watch-skill]
command = "uvx"
args = ["--from", "watch-skill[standard]", "watch-skill", "serve"]

(Codex CLI ≥ 0.20; older versions use the same table under [mcp_servers].)

Smoke test (3 steps)

  1. codex → in the session run /mcp to confirm watch-skill is connected.
  2. Prompt: "Use watch-skill to watch https://www.youtube.com/watch?v=aqz-KE-bpKQ and tell me what happens at 0:10."
  3. Follow up: "list the videos watch-skill has indexed" → list_videos.

Notes

  • Codex consumes the text report (frame paths + transcript). The adapters/agents-md/AGENTS.md block teaches Codex when to reach for each tool — paste it into your repo's AGENTS.md.
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. yesterday First seen · 57 lines · 0 tokens per session scan B 37f6a06e435a

Subscribe to this mod's changes

codex-cli is an agent published in the GitHub repository oxbshw/watch-skill (320 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 488 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ProductivityTestingWriting and docsagent-toolsai-agentsclaudeclaude-codecomputer-visionffmpeg
Related

Other agents, from other repositories

project-auditor

Read-only health audit of the VibeFrame monorepo. Use for a periodic project review — structure, CLI/doc drift, dead code, dependency hygiene, test/lint health, and tech debt — producing a prioritized cleanup plan. Proposes actions; does not make sweeping edits.

vericontext/vibeframe · 62 tokens

AGENTS.motiscope

Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.

KumarSashank/motiscope · 0 tokens

qa-reviewer

Deterministic reviewer persona for manual agent-dispatch checks.

itlackey/akm · 15 tokens

custom_agent

Execute a custom agent configuration by its UUID.

Alation/alation-ai-agent-sdk · 0 tokens

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

spiritledsoftware/caplets · 0 tokens

query_flow_agent

Query Flow Agent for data product query workflow management.

Alation/alation-ai-agent-sdk · 0 tokens