agentic-vbench AGENTS.md

Repository instructions for agentic-vbench, a project containing tasks for repairing, assembling, ordering, and repurposing video.

In plain words
What is it for?
Use them when changing the repository, locating task families, checking current behavior before making decisions, or adding project-wide development conventions.
Why use it?
They give coding agents the project layout, rules, and commands needed to work consistently, including which instructions apply inside subfolders.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/philolabs/agentic-vbench/agents-md
Clone the repo
git clone --depth 1 https://github.com/PhiloLabs/agentic-vbench

Made for: Codex, OpenCode.

Per session 887 This file is loaded in full into every session.
When invoked 887 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00887 $0.00887
Opus 5 $0.00443 $0.00443
Sonnet 5 $0.00177 $0.00177
Haiku 4.5 $0.00089 $0.00089

Measured 3d ago against content hash 62f6fde8a9fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-vbench 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 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.

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.

AGENTS.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Telegraph style. Root rules only. Read scoped AGENTS.md before subtree work.

Start

  • Repo: agentic-vbench. Greenfield; conventions still forming — keep changes minimal and reversible.
  • Replies: repo-root refs only, e.g. src/foo.ts:80. No absolute paths, no ~/.
  • Verify before deciding. Read source/tests/current behavior; do not assume APIs, defaults, or runtime from prior knowledge.
  • This file is policy; docs/ (when added) is explanation; code/config is the contract. Link across layers, never duplicate.
  • Add new conventions/workflows here (or in a scoped AGENTS.md) — not in a code comment or commit message.
  • New AGENTS.md in any subtree: add a sibling CLAUDE.md symlink (ln -s AGENTS.md CLAUDE.md).

Map

  • tasks/ — Harbor task dirs, grouped into 4 family subdirs:
    • tasks/agentic_vbench_repair/ — 18 exp-* audio/video repair tasks (audio / color / deblur / sr / swap / glitch / cut / disfluency).
    • tasks/agentic_vbench_assembly/ — 18 video-assembly tasks (agentic-vbench-assembly-task<N>).
    • tasks/agentic_vbench_sequencing/ — 28 video-ordering tasks (agentic-vbench-sequencing-task<N>).
    • tasks/agentic_vbench_repurpose/ — 36 long-form-to-short-vertical repurpose tasks (per-task creative brief + LLM-judged rubric). Downstream tools resolve task names to paths via scripts/_task_paths.py (task_dir(name), all_tasks(family=…)), so adding/renaming families means touching one file.
  • scripts/ — the Harbor wrapper. install-harbor.sh pins the Harbor CLI; parallel_rollout.py schedules harbor run across many tasks against either local Docker or Modal; monitor_job.py tails a running trial; _task_paths.py is the name→path resolver. Tasks are evaluated using the verifier code shipped under each task's steps/solve/tests/; Harbor produces the per-trial reward.json.
  • docs/VERIFIER_DESIGN.md — load-bearing doc for the verifier math (universal normalize-improvement).
  • jobs/, site/, logs/, experiments/ — runtime / local-only outputs (gitignored).
  • Scoped AGENTS.md files: none yet. Add one when a subtree has rules that genuinely differ from root.

Read the full file on GitHub · 54 lines

Changes

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.

  1. 3d ago First seen · 54 lines · 887 tokens per session scan A 62f6fde8a9fc

Subscribe to this mod's changes

agentic-vbench AGENTS.md is an instructions file published in the GitHub repository PhiloLabs/agentic-vbench (89 stars, last pushed 4d ago), licensed Apache-2.0. It adds 887 tokens to every session, about $0.0044 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 2026-08-30.