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.
/plugin marketplace add danielrosehill/Claude-AI-Video-Producer-Plugin/plugin install ai-video-producerWrote 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/danielrosehill/claude-ai-video-producer-plugin/setup-credentials)<a href="https://agentmods.dev/commands/danielrosehill/claude-ai-video-producer-plugin/setup-credentials"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-ai-video-producer-plugin/setup-credentials/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/danielrosehill/claude-ai-video-producer-plugin/setup-credentials"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-ai-video-producer-plugin/setup-credentials.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 | $0.00058 | $0.01246 |
| Opus 5 | $0.00029 | $0.00623 |
| Sonnet 5 | $0.00012 | $0.00249 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade D, and why
setup-credentials scanned grade D with 3 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Don't `chmod 600` if the file already has tighter permissions. Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- The MiniMax MCP runs via `uvx`; if `uvx` isn't on PATH, install with `curl -LsSf https://astral.sh/uv/install.sh | sh`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- The MiniMax MCP runs via `uvx`; if `uvx` isn't on PATH, install with `curl -LsSf https://astral.sh/uv/install.sh | sh`. How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up persistent credentials for the bundled MCP servers (fal.ai, Replicate, MiniMax) and SDK runners (fal-js, WaveSpeed Python), then bootstrap the runner toolchains.
Steps
-
Check if
~/.config/ai-video-producer/.envalready exists.- If yes, read it (do not echo the values back) and report which keys are already set. Ask the user if they want to update any.
- If no, create the directory:
mkdir -p ~/.config/ai-video-producer.
-
Prompt the user for each missing value:
FAL_KEY— fal.ai API key (https://fal.ai/dashboard/keys). Used by the hosted MCP server athttps://mcp.fal.ai/mcpand byrunners/fal_run.mjs.REPLICATE_API_TOKEN— Replicate API token (https://replicate.com/account/api-tokens). Used by the localreplicate-mcpnpm package.WAVESPEED_API_KEY— WaveSpeedAI key (https://wavespeed.ai/accesskey). Used byrunners/wavespeed_run.py.MINIMAX_API_KEY— MiniMax key. Used by the bundledminimax-mcpserver. Region matters: Global keys come from https://www.minimax.io/platform/user-center/basic-information/interface-key, Mainland from https://platform.minimaxi.com/user-center/basic-information/interface-key.MINIMAX_API_HOST—https://api.minimax.io(Global) orhttps://api.minimaxi.com(Mainland). Must match the key region or the MCP returns "Invalid API key".MINIMAX_MCP_BASE_PATH— local output directory MiniMax should write generated media into (default:$HOME/Videos/minimax).MINIMAX_API_RESOURCE_MODE—url(default) orlocal.
Accept blank to skip a key. Each provider degrades independently (skipping
WAVESPEED_API_KEYjust means the wavespeed runner won't work; skippingMINIMAX_API_KEYdisables the minimax MCP). -
Write
~/.config/ai-video-producer/.envwithKEY=valuelines. Mode600. -
Ensure the env loader is in the user's shell profile. Detect the shell from
$SHELL(default~/.bashrc; for zsh use~/.zshrc). The loader line:# AI Video Producer credentials [ -f "$HOME/.config/ai-video-producer/.env" ] && set -a && . "$HOME/.config/ai-video-producer/.env" && set +a- If the line is already present, do nothing.
- If not, append it. Tell the user to either start a new shell or
sourcetheir profile to pick up the values for the current session.
-
Verify by running (in a subshell that sources the profile):
bash -lc 'for k in FAL_KEY REPLICATE_API_TOKEN WAVESPEED_API_KEY MINIMAX_API_KEY MINIMAX_API_HOST; do v="${!k}"; echo "$k: ${v:+set}${v:-MISSING}"; done'Report which are
setand which areMISSING. Do not print the actual key values. -
Bootstrap runner toolchains. The SDK runners under
runners/need their own deps installed once per machine. Resolve${CLAUDE_PLUGIN_ROOT}/runners(or fall back to the repo'srunners/directory if running from a checkout) and:- fal-js:
cd runners && npm install— installs@fal-ai/clientforfal_run.mjs. Skip ifrunners/node_modules/@fal-ai/clientalready exists. - WaveSpeed Python: prefer a venv. Check for
runners/.venv; if absent, create withpython3 -m venv runners/.venv. Thenrunners/.venv/bin/pip install -r runners/requirements.txt. If the user has a global preference forpipx/system pip, ask before creating the venv.
Skip whichever toolchain corresponds to a key the user left blank.
- fal-js:
-
Tell the user how to confirm the runners work:
FAL_KEY=$FAL_KEY node runners/fal_run.mjs --help 2>&1 | head -3 # should print usage runners/.venv/bin/python runners/wavespeed_run.py --help # should print usage -
Remind the user that:
- Claude Code reads env vars from the process it inherits — so any new Claude Code session started from a shell that has sourced
.envwill see the keys. - To use the keys right now in this session, the user can either restart Claude Code from a fresh shell, or export the values manually for the current process.
- The MiniMax MCP runs via
uvx; ifuvxisn't on PATH, install withcurl -LsSf https://astral.sh/uv/install.sh | sh.
- Claude Code reads env vars from the process it inherits — so any new Claude Code session started from a shell that has sourced
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.
- 12d ago First seen · 66 lines · 58 tokens per session scan D c71b44bdc2d7
setup-credentials is a command published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,246 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.