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 instructions/yansilinta/video-agent-runtime/agents-mdgit clone --depth 1 https://github.com/YansIlinta/video-agent-runtimeWrote 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/instructions/yansilinta/video-agent-runtime/agents-md)<a href="https://agentmods.dev/instructions/yansilinta/video-agent-runtime/agents-md"><img src="https://agentmods.dev/badge/instructions/yansilinta/video-agent-runtime/agents-md.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 | $0.01354 | $0.01354 |
| Opus 5 | $0.00677 | $0.00677 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
video-agent-runtime AGENTS.md scanned grade A 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 3d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `child_process` How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository rules for coding agents
This repository is developed with coding agents, but the agent is not the product architecture. Before changing code, preserve the runtime invariants below.
Start with the narrowest relevant context
Read only what the task needs:
- Product behavior and public positioning:
README.md - Day-to-day engineering setup:
docs/development.md - Domain/runtime architecture:
docs/architecture.md - Security and secret handling:
docs/security.md - Speech models and provider choices:
docs/speech-models-2026.md - Voice identity / cloning / design:
docs/voice-identity.md - Mobile host:
docs/mobile/README.md - Agent-facing video-editing workflow:
skills/video-editing/SKILL.md
Do not load every document for every task.
Authoritative architecture
The following shared domain/runtime concepts remain authoritative across CLI, MCP, Control API, Node and Mobile hosts:
VideoAgentCore
Project / ProjectRepository
Workflow
Transcript
EditingStrategy
EditPlan
EditPatch
Timeline
Version
Job / JobEvent
ProviderCall
Provider contracts
Renderer contracts
Do not introduce:
- a mobile-only editing domain;
- a second Timeline model;
- a second Workflow state machine for the same project flow;
- a second durable Job Queue;
- transport-specific project mutation logic;
- a provider-specific branch inside core domain logic when capability discovery can express the difference.
A lightweight transport such as speech-mcp may avoid constructing the full project runtime, but it should reuse shared provider/runtime contracts instead of cloning implementations.
LLM and edit-state rules
LLM output is proposal data, not authoritative project state.
The expected direction is:
LLM
→ structured schema
→ validation
→ semantic validation
→ diff
→ apply
→ immutable Version
→ render
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.
- 3d ago First seen · 227 lines · 1,354 tokens per session scan A 048d925d7339
video-agent-runtime AGENTS.md is an instructions file published in the GitHub repository YansIlinta/video-agent-runtime (1 stars, last pushed 9d ago), licensed MIT. It adds 1,354 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
mistral-mcp CLAUDE.md
Instructions for Swih/mistral-mcp, covering claude.md — mistral-mcp, 1. identité du projet, 2. règles dures (ne pas transgresser), 3. layout & responsabilités and 4. conventions de code.
pfsense-mcp-server AGENTS.md
Instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
trello-mcp AGENTS.md
Instructions for enthouan/trello-mcp, covering agents.md, project summary, hard constraints, runtime and package manager and common commands.
leclap CLAUDE.md
Instructions for heristop/leclap: This repository's agent guidance lives in AGENTS.md — read it first; it is the single source of truth for structure, commands, and conventions.