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/t0msilver/vidtheque/agents-mdgit clone --depth 1 https://github.com/T0mSIlver/vidthequeWhat 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 | $0.00990 | $0.00990 |
| Opus 5 | $0.00495 | $0.00495 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
vidtheque AGENTS.md 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 2d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — how to work in this repo
vidtheque turns the videos you follow into timestamped, receipt-backed
knowledge for you and your agents. Owner: Tom Vaucourt. MIT. This file is the
working conventions, kept short because it loads into every session; the
product itself is explained in README.md and docs/README.md.
Ground truth, in order
docs/design/*.md— the contracts (DECISIONS.mdoutranks the rest). If implementation must diverge, amend the contract in the same commit and say why.positioning.mdis LOCKED: all public-facing copy follows it.research/— append-only evidence (index:research/README.md; founding decisions:research/HANDOFF-2026-08-08.md). Add dated sections; never rewrite or delete.DESIGN.md+PRODUCT.md— the visual contract for the web surfaces.- This file — conventions only. Any doc above wins.
docs/ROADMAP.md is the only list of open work — a backlog inside a dated
document is a snapshot and goes stale silently. docs/LESSONS.md holds the
operational rules an incident or a launch paid for.
Invariants — never change these without Tom
mcp/↔worker/is HTTP only. No Python imports across the boundary, not even in tests. The worker is stateless inference; all state lives in mcp/.- Two time axes, never overloaded:
published_*picks videos,offset_*picks positions inside one. allmeans all — a filter that can't apply to a leg prints anote:, never silently narrows.- Token discipline: middle-truncation with a documented
0opt-out, pagination hints printed in payloads, double caps (items AND chars), expensive paths bounded independently oflimit, server-side clamps — never prompt-only limits. - Frames by authenticated URL by default; inline base64 is the opt-in, with the correct mimeType.
has_moreover exact totals; relevance-first ordering,orderexplicit.
Working here
- Python 3.12,
uvworkspace (mcp/,worker/).make testis CPU-only and must stay green — tests never download models or need a GPU.make benchis manual, Tom's box only. - Deterministic builds: committed
uv.lock, digest-pinned CUDA base image. Dependency bumps are deliberate commits, not side effects. deploy/.env.exampleis the document of record for every env var — a new env without an entry there is a bug.- No self-hosted CI runners, ever (public repo, drive-by PR risk).
- Tom's box (3090, llama.cpp VRAM lease via
GPU_ACQUIRE_CMDhooks) is context for deploy work, not a shipped default — see the founding handoff.
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.
- 2d ago First seen · 76 lines · 990 tokens per session scan A 307ec661622c
vidtheque AGENTS.md is an instructions file published in the GitHub repository T0mSIlver/vidtheque (2 stars, last pushed 2d ago), licensed MIT. It adds 990 tokens to every session, about $0.0049 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 instructions, from other repositories
metube AGENTS.md
AGENTS.md instructions for alexta69/metube, covering agent guidelines, project scope — read this before planning a feature, readme.md size constraint, tech stack and build & test commands.
VaultysClaw CLAUDE.md
Instructions for vaultys/VaultysClaw, covering claude.md, commands, development, demo / simulator and build.
lobster0 AGENTS.md
Instructions for NEDONION/lobster0, covering lobster0 agent 工程规范, 适用范围与优先级, 项目事实, 常用命令 and 首次安装或依赖变化后.
homelab-monitor CLAUDE.md
Instructions for SikamikanikoBG/homelab-monitor, covering claude.md and conventions.
agentgram CLAUDE.md
Instructions for agentgram/agentgram, covering claude.md — agentgram development guide, project overview, tech stack, monorepo structure and core architecture patterns.
powerbrain CLAUDE.md
Instructions for nuetzliches/powerbrain, covering claude.md — powerbrain context engine, project overview, architecture, directory structure and components and ports.