semantic-linefeeds AGENTS.md

semantic-linefeeds AGENTS.md is an instructions file for Codex, OpenCode from arloliu/semantic-linefeeds. It costs 508 tokens per session, scanned A, original, Apache-2.0.

Project instructions for semantic-linefeeds, a checker that requires one clear thought per line in comments, documentation, docstrings, and Markdown.

In plain words
What is it for?
Editing semantic-linefeeds, checking touched files, following its self-hosting rule, and maintaining its Python checker and agent integrations.
Why use it?
They explain the repository's writing rules and validation command so changes do not fail its formatting checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

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/arloliu/semantic-linefeeds/agents-md
Clone the repo
git clone --depth 1 https://github.com/arloliu/semantic-linefeeds

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for semantic-linefeeds AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arloliu/semantic-linefeeds/agents-md.svg)](https://agentmods.dev/instructions/arloliu/semantic-linefeeds/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/arloliu/semantic-linefeeds/agents-md"><img src="https://agentmods.dev/badge/instructions/arloliu/semantic-linefeeds/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 508 This file is loaded in full into every session.
When invoked 508 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 5.1 $0.00508 $0.00508
Opus 5 $0.00254 $0.00254
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 5d ago against content hash ea15c61db0ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

semantic-linefeeds 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 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.

AGENTS.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic-Linefeeds Agent Configuration

Authoritative entrypoint for coding agents in this repository. CLAUDE.md points here; other agents read AGENTS.md directly. If instructions here conflict with a default behavior, this file and the rules it references win — only an explicit user instruction overrides them.

Semantic-linefeeds enforces one-thought-per-line prose in code comments, doc comments, docstrings, and Markdown. One stdlib-only Python core (scripts/check_linefeeds.py) does all checking; thin adapters connect it to Claude Code, Codex CLI, and opencode.

Self-Hosting Rule

Every Markdown file in this repo must itself pass the checker:

python3 scripts/check_linefeeds.py --file <files you touched>

Zero fused/wrap findings before any commit; long findings are advisories you judge, not obey.

Test data under tests/ is the one exception, and it is not prose. Those files exist to carry text the checker must flag or must leave alone, so their findings are the measurement rather than a defect. Write prose with semantic line breaks from the first draft: one sentence per line, and a long sentence splits only at a real clause boundary.

Rules

Read .agents/rules/AGENTS.md first — it maps task triggers to the rule files that apply.

000-agent-contract.md is always in force, including its core rule: do not guess when source, tests, docs, git, or grep can answer.

Two things to know before you touch code:

  • The core stays one file (100): scripts/check_linefeeds.py, Python 3.9+, stdlib imports only. Every adapter depends on the "copy one file, runs on bare python3" property.
  • Precision over recall (100): the checker flags suspicion and the agent judges; a missed finding is acceptable, but a false positive is a bug.

Validation

Run before calling any work done:

Read the full file on GitHub · 60 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. 5d ago First seen · 60 lines · 508 tokens per session scan A ea15c61db0ab

Subscribe to this mod's changes

semantic-linefeeds AGENTS.md is an instructions file published in the GitHub repository arloliu/semantic-linefeeds (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 508 tokens to every session, about $0.0025 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.