YSCV AGENTS.md

Repository instructions for YSCV, a project whose contributors include both people and coding agents. They define responsibility, required checks, and the workflow for proposing changes.

In plain words
What is it for?
Use them before preparing or reviewing YSCV changes, especially when checking the required local tests, performance measurements, and pull-request responsibilities.
Why use it?
They make clear that the person submitting a change remains responsible for understanding it, testing it, and supporting any claims about it.

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/enthropy7/yscv/agents-md
Clone the repo
git clone --depth 1 https://github.com/enthropy7/YSCV

Made for: Codex, OpenCode.

Per session 2,988 This file is loaded in full into every session.
When invoked 2,988 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 $0.02988 $0.02988
Opus 5 $0.01494 $0.01494
Sonnet 5 $0.00598 $0.00598
Haiku 4.5 $0.00299 $0.00299

Measured 2d ago against content hash c710b6d176b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

YSCV 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.

AGENTS.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — rules for AI coding agents working on yscv

This file is the contract between this repository and any AI coding agent (Claude Code, Copilot Workspace, Cursor, Aider, etc.) that proposes changes here. Concrete, enforceable, short.

The same rules apply to human contributors.


Responsibility

Every PR has exactly one responsible party: the human who opens it. This holds whether the diff was hand-typed, drafted by an agent, or copy-pasted from a chat log. By submitting, you assert four things about the change:

  1. You have the right to submit it under this repository's licence.
  2. You have read the code you are submitting and understand what it does. If asked "why this line?", you can answer without re-prompting an agent.
  3. You have run the local gates listed in section 2 and the result is what you say it is. "The agent said tests pass" is not a substitute for running them.
  4. For any performance claim, you measured it yourself on your own hardware and the numbers in the PR description are yours.

There is no "the agent did it" defence. A regression introduced by an agent-drafted patch is the submitter's regression, and reverting or fixing it is the submitter's job.

Disclosure of method: if a change is non-trivial and was drafted with an agent, mention that in the PR description in one line — what the agent did, what you verified. This is for context, not credit; do not add Co-Authored-By: lines for the agent (see section 3).

Anonymous or pseudonymous PRs that exist only to relay agent output without a human standing behind them will be closed unread.


0. Read these first, in order

  1. CONTRIBUTING.md — project priorities and the change workflow.
  2. docs/feature-flags.md — what each Cargo feature does, when to enable it, runtime env knobs.
  3. docs/architecture.md — the high-level shape of the workspace, dispatch boundaries, dataflow.
  4. The crate-local README.md of the crate you are touching.
  5. The latest docs/perf-arc-*.md if you're touching a hot path — it lists what landed, what was tried and reverted, and why.

Read the full file on GitHub · 318 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. 2d ago First seen · 318 lines · 2,988 tokens per session scan A c710b6d176b0

Subscribe to this mod's changes

YSCV AGENTS.md is an instructions file published in the GitHub repository enthropy7/YSCV (49 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,988 tokens to every session, about $0.0149 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.

Related

Other instructions, from other repositories

bubbaloop CLAUDE.md

Instructions for kornia/bubbaloop, covering 🦐 bubbaloop, living documents (update these as architecture evolves), structure, node sdk (crates/bubbaloop-node/) and node build helper (crates/bubbaloop-node-build/).

kornia/bubbaloop · 4,789 tokens

model_guided_research CLAUDE.md

Claude Code instructions for Dicklesworthstone/model_guided_research: RULE NUMBER 1 (NEVER EVER EVER FORGET THIS RULE!!!): YOU ARE NEVER ALLOWED TO DELETE A FILE WITHOUT EXPRESS PERMISSION FROM ME OR A DIRECT COMMAND FROM ME. EVEN A NEW FILE THAT YOU YOURSELF CREATED, SUCH AS A TEST CODE FILE. YOU HAVE A HORRIBLE…

Dicklesworthstone/model_guided_research · 636 tokens

model_guided_research AGENTS.md

AGENTS.md instructions for Dicklesworthstone/model_guided_research, covering mcp agent mail — multi-agent coordination, issue tracking with br (beadsrust), basics, using bv as an ai sidecar and morph warp grep — ai-powered code search.

Dicklesworthstone/model_guided_research · 4,466 tokens

tensors-to-consciousness AGENTS.md

AGENTS.md instructions for alexhraber/tensors-to-consciousness, covering agents.md — universal agent contract, mandatory orientation, mandatory initialization, control-plane first loop and pre-inference governance.

alexhraber/tensors-to-consciousness · 1,496 tokens

tensors-to-consciousness CLAUDE.md

Claude Code instructions for alexhraber/tensors-to-consciousness, covering claude.md - agent entrypoint, orientation & documentation, project context, quick start and control-plane first.

alexhraber/tensors-to-consciousness · 652 tokens

tensors-to-consciousness GEMINI.md

Gemini CLI instructions for alexhraber/tensors-to-consciousness, covering gemini.md - agent entrypoint, orientation & documentation, project context, quick start and control-plane first.

alexhraber/tensors-to-consciousness · 651 tokens