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/arloliu/semantic-linefeeds/agents-mdgit clone --depth 1 https://github.com/arloliu/semantic-linefeedsWrote 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/arloliu/semantic-linefeeds/agents-md)<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>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 5.1 | $0.00508 | $0.00508 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
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.
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:
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.
- 5d ago First seen · 60 lines · 508 tokens per session scan A ea15c61db0ab
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.
Other instructions, from other repositories
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
telegramify-markdown AGENTS.md
Instructions for sudoskys/telegramify-markdown, covering telegramify-markdown agent guide, task routing, quick commands, project rules and architecture map.
easy-notion-mcp CLAUDE.md
Claude Code instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
markview CLAUDE.md
Instructions for paulhkang94/markview, covering markview — ai development guide, quick reference, architecture, mcp tools (for ai integration) and safety rules.