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 agentmods add commands/galbaz1/video-research-mcp/explainergit clone --depth 1 https://github.com/Galbaz1/video-research-mcpWrote 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/galbaz1/video-research-mcp/explainer)<a href="https://agentmods.dev/commands/galbaz1/video-research-mcp/explainer"><img src="https://agentmods.dev/badge/commands/galbaz1/video-research-mcp/explainer.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.01197 |
| Opus 5 | $0.00009 | $0.00598 |
| Sonnet 5 | $0.00003 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade B, and why
explainer 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Use `Glob` to find recent `~/.claude/projects/*/memory/gr/*/analysis.md` files How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explainer Video: $ARGUMENTS
Create and produce an explainer video from content.
Phase 0: Onboarding (when no arguments)
If $ARGUMENTS is empty, guide the user:
AskUserQuestion:
questions:
- question: "What kind of video do you want to create?"
header: "Video type"
multiSelect: false
options:
- label: "From a Production Order"
description: "Use an existing POD file (docs/plans/*.md) as the blueprint"
- label: "From research output"
description: "Turn a /gr:video or /gr:research analysis into a video"
- label: "From scratch"
description: "Start with a topic — I'll help you build the content"
- label: "Check existing projects"
description: "See what projects exist and their status"
If "From a Production Order":
- Use
Globto finddocs/plans/*POD*.mdordocs/plans/*VIDEO*.md - Present the found files and let the user pick
- Read the POD file to extract: script, storyboard, audio direction
- Create project and inject the POD content
If "From research output":
- Use
Globto find recent~/.claude/projects/*/memory/gr/*/analysis.mdfiles - Present the top 5 most recent analyses
- Let the user pick one (or multiple) as source material
If "From scratch":
- Ask for the topic
- Suggest running
/gr:researchor/gr:videofirst to gather source material - Or proceed directly with user-provided text
If "Check existing projects":
- Call
explainer_list()to show all projects with their status
Phase 1: Setup
If $ARGUMENTS is a project ID that doesn't exist yet:
- Call
explainer_create(project_id="$ARGUMENTS") - Ask the user for content to inject, or look for files in the current directory
If the project exists, call explainer_status to see current progress.
Phase 2: Content Injection
If the project's input/ is empty:
- Ask the user for content (research output, markdown, text)
- Call
explainer_inject(project_id, content, filename)to write it
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.
- 5d ago First seen · 113 lines · 17 tokens per session scan B 45c763b3f153
explainer is a command published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,197 once invoked, about $0.0001 per session on Opus 5. 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.
Other commands, from other repositories
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.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.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.specify
Create or update the feature specification from a natural language feature description.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.