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/scidsg/hushline/agents-mdgit clone --depth 1 https://github.com/scidsg/hushlineWrote 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/scidsg/hushline/agents-md)<a href="https://agentmods.dev/instructions/scidsg/hushline/agents-md"><img src="https://agentmods.dev/badge/instructions/scidsg/hushline/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 | $0.02590 | $0.02590 |
| Opus 5 | $0.01295 | $0.01295 |
| Sonnet 5 | $0.00518 | $0.00518 |
| Haiku 4.5 | $0.00259 | $0.00259 |
Grade A, and why
hushline 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 3d ago First seen · 186 lines · 2,590 tokens per session scan A 3004425610a7
hushline AGENTS.md is an instructions file published in the GitHub repository scidsg/hushline (132 stars, last pushed 10d ago), licensed AGPL-3.0. It adds 2,590 tokens to every session, about $0.0129 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.
Other instructions, from other repositories
VayuPress AGENTS.md
Instructions for johalputt/VayuPress, covering agents.md — instructions for ai agents working in this repo and releases: micro by default, roll over at 99.
Ghost AGENTS.md
AGENTS.md instructions for TryGhost/Ghost, covering agents.md, required workflow, repository skills and task routing and important warnings.
SarvTerminal AGENTS.md
Instructions for Sarv/SarvTerminal, covering agent development guide, commands, libghostty-vt, directory structure and linux/gtk port roadmap (linux-roadmap.md).
IronMesh AGENTS.md
Instructions for WizTheAgent/IronMesh, covering agent guide for this repository, what ironmesh is, quick repo orientation, non-negotiable operating rules and workflow for changes.
autopunk-media-skills CLAUDE.md
Instructions for ur-grue/autopunk-media-skills, covering autopunk-media-skills, what this project is, language rule, anonymity rule and repository structure.
jor-mcp AGENTS.md
Instructions for ambiental-media/jor-mcp, covering ai agent instructions for jor-mcp, project context, prerequisite: development standards, code style, conventions & python best practices and 1. file structure, imports & project layout.