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/katareayush/video-captions/seedgit clone --depth 1 https://github.com/katareayush/video-captionsWrote 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/katareayush/video-captions/seed)<a href="https://agentmods.dev/commands/katareayush/video-captions/seed"><img src="https://agentmods.dev/badge/commands/katareayush/video-captions/seed.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 5.1 | $0.00015 | $0.00836 |
| Opus 5 | $0.00008 | $0.00418 |
| Sonnet 5 | $0.00003 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
seed 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 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.
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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are generating a test-data seed script for the current repository. Be surgical and concise — produce something that runs on the first try.
User request/filters: $ARGUMENTS
1. Analyze the repo (read, don't guess)
Detect the stack and locate every place data is defined. Check for, in order of what exists:
- SQL / migrations:
*.sql,migrations/,schema.sql, Flyway/Liquibase. - ORM schemas: Prisma (
schema.prisma), Django (models.py), SQLAlchemy, TypeORM/Sequelize/Mongoose, Rails (db/schema.rb), Laravel migrations, GORM/Ent structs, Ecto. - Python: dataclasses, Pydantic models,
models.py. - Web3: Solidity (
*.sol), Hardhat/Foundry configs, ABI JSON, deploy scripts — data = on-chain seeding (mint, deploy, fund accounts, populate mappings). - APIs / types: OpenAPI/GraphQL schemas, TypeScript interfaces, protobuf.
- Config:
.env.example,docker-compose.yml, package manifest (package.json,pyproject.toml,Cargo.toml,go.mod,Gemfile) to learn the runtime, DB, and how existing scripts run.
Extract: entities/tables, field types, enums, NOT NULL / required, unique constraints, foreign keys and insertion order, and default values.
2. Pick the right output
Write the seed script in the project's own language and idiom so it drops in cleanly:
- Use the project's existing DB client / ORM / connection config (reuse
.env, never hardcode secrets). - Prefer the project's existing faker/factory lib if present; otherwise use a lightweight, well-known one for that ecosystem (
@faker-js/faker,faker/Faker, etc.), and add it to the manifest. - Respect FK order, satisfy every constraint, cover enums with a spread of values, and produce referentially consistent data (child rows point at real parents).
- Make it idempotent (safe to re-run: truncate/upsert or guard) and parameterized by count.
- Web3: emit a script for the project's toolchain (Hardhat/Foundry/ethers/web3.py) that deploys/uses contracts and seeds on-chain state against a local node.
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 · 44 lines · 15 tokens per session scan A 2a563a73a6da
seed is a command published in the GitHub repository katareayush/video-captions (8 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 836 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.
Other commands, from other repositories
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
index
Visual overview of Beacon index — chunks, coverage, provider. Pass --files to list indexed files.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.