hline-usage

hline-usage is a skill for Claude Code, Codex from chennest/hline. It costs 40 tokens per session (1,085 once invoked), scanned A, original, MIT.

A guide for using hcat and hsed to read and edit remote files over SSH. SSH is a way to work with a computer over a network; these tools use content-based anchors so edits remain tied to the intended lines.

In plain words
What is it for?
Use it to inspect local-text files on remote machines with hcat and make anchored replacements, additions, or insertions with hsed. It is not intended for local files, binary files, or non-UTF-8 text.
Why use it?
It provides a safer way to locate and change text on remote servers when ordinary line numbers or fragile text matching could target the wrong content.

Skill for Claude CodeCodex

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 skills/chennest/hline/hline-usage
Any agent
npx skills add chennest/hline --skill hline-usage
Clone the repo
git clone --depth 1 https://github.com/chennest/hline

Made for: Claude Code, Codex.

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 hline-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/chennest/hline/hline-usage.svg)](https://agentmods.dev/skills/chennest/hline/hline-usage)
Your own site
<a href="https://agentmods.dev/skills/chennest/hline/hline-usage"><img src="https://agentmods.dev/badge/skills/chennest/hline/hline-usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,085 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00040 $0.01085
Opus 5 $0.00020 $0.00543
Sonnet 5 $0.00008 $0.00217
Haiku 4.5 $0.00004 $0.00109

Measured 4d ago against content hash b5abc8b8e721, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hline-usage 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 4d 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.

hline-usage/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hline Usage Guide for AI Agents

Overview

hline = hcat (view) + hsed (edit). Hash-anchored file operations for SSH environments. Zero dependencies, single binary.

  • hcat — Read files with hash anchors on each line
  • hsed — Edit files via those anchors (replace / append / prepend)

Repo: https://github.com/chennest/hline | Install: see README

When to Use

  • SSH access to a remote server with hcat/hsed installed
  • Need to read/edit files unreachable by native agent tools
  • sed is too fragile for the edit

Do NOT use for: local files (use native tools), binary files, non-UTF-8 content.

How It Works

Each line gets a 2-char hash anchor based on its content (not position). Hash binds to content only — insertions/deletions elsewhere won't invalidate anchors on untouched lines.

Format: {line_number}#{hash}|{content}

11#XJ| function hello() {
12#MB|   return "world";
13#QR| }

hcat — View Files

hcat /path/to/file              # Full file
hcat /path/to/file 5-10         # Lines 5-10
hcat /path/to/file 5            # Line 5 to EOF
hcat /path/to/file 5 +10        # Line 5 + next 10 lines
hcat /path/to/file -A 3 5       # Line 5 + 3 after (space required)
hcat /path/to/file -B 2 -A 3 5  # Line 5 + 2 before + 3 after

⚠️ -A/-B require space: -A 3 ✓, -A3

hsed — Edit Files

Usage: hsed <file> <operation> <anchor(s)> << 'EOF' then content, then EOF.

# Replace single line
hsed /path/to/file replace 11#XJ << 'EOF'
new content
EOF

# Replace range (start anchor, end anchor)
hsed /path/to/file replace 11#XJ 13#QR << 'EOF'
multi-line replacement
EOF

# Delete range (empty content)
hsed /path/to/file replace 11#XJ 13#QR << 'EOF'
EOF

# Insert after a line
hsed /path/to/file append 13#QR << 'EOF'
inserted content
EOF

# Insert before a line
hsed /path/to/file prepend 11#XJ << 'EOF'
inserted content
EOF

# Preview (dry-run, no write)
hsed -p /path/to/file replace 11#XJ << 'EOF'
new content
EOF

Read the full file on GitHub · 123 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. 4d ago First seen · 123 lines · 40 tokens per session scan A b5abc8b8e721

Subscribe to this mod's changes

hline-usage is a skill published in the GitHub repository chennest/hline (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,085 once invoked, about $0.0002 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.