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.
git clone --depth 1 https://github.com/fredrikaverpil/claudelineWrote 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/commands/fredrikaverpil/claudeline/setup)<a href="https://agentmods.dev/commands/fredrikaverpil/claudeline/setup"><img src="https://agentmods.dev/badge/commands/fredrikaverpil/claudeline/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/fredrikaverpil/claudeline/setup"><img src="https://agentmods.dev/badge/commands/fredrikaverpil/claudeline/setup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00613 |
| Opus 5.5 | $0.00000 | $0.00245 |
| Sonnet 5.5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade B, and why
setup scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL "https://github.com/fredrikaverpil/claudeline/releases/latest/download/claudeline_${OS}_${ARCH}.tar.gz" | tar -xz -C <target_directory> claudeline How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup claudeline
Install and configure the claudeline plugin as your Claude Code statusline.
Re-running this command will update claudeline to the latest version.
Steps
- Check if claudeline is already installed.
Check if a claudeline binary already exists on the system:
which claudeline
If found, note the path — the update should replace the binary at that location.
If not found, check these paths:
~/.local/bin/claudeline~/go/bin/claudeline
- Download the latest pre-built binary from GitHub releases.
Detect OS and architecture:
OS=$(uname -s | tr '[:upper:]' '[:lower:]')
ARCH=$(uname -m)
case "$ARCH" in
x86_64) ARCH="amd64" ;;
aarch64) ARCH="arm64" ;;
esac
Download and install to the target directory (the directory from step 1):
mkdir -p <target_directory>
curl -fsSL "https://github.com/fredrikaverpil/claudeline/releases/latest/download/claudeline_${OS}_${ARCH}.tar.gz" | tar -xz -C <target_directory> claudeline
chmod +x <target_directory>/claudeline
If the download fails (e.g. curl is not available, no internet, or the
platform is unsupported), fall back to go install:
go install github.com/fredrikaverpil/claudeline@latest
This requires Go to be installed with $GOPATH/bin in $PATH.
- Verify the binary is available.
<target_directory>/claudeline -version
- Configure
settings.jsonif not already set.
Determine the settings file path: use $CLAUDE_CONFIG_DIR/settings.json if the
CLAUDE_CONFIG_DIR environment variable is set, otherwise
~/.claude/settings.json.
Read the settings file. If statusLine is already configured and its command
contains claudeline, skip this step — the existing configuration is valid.
Otherwise, set the statusLine field. If the target directory is in the user's
$PATH, use just the binary name:
{
"statusLine": {
"type": "command",
"command": "claudeline"
}
}
Otherwise, use the full path:
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.
- 2mo ago First seen · 96 lines · 0 tokens per session scan B aeea372297b5
setup is a command published in the GitHub repository fredrikaverpil/claudeline (55 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 613 tokens. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
setup compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupfredrikaverpil/claudeline | Command | 55 | 25d ago | MIT | B | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 149k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 149k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 149k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 149k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 149k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 149k | yesterday | MIT | A | 14 | Claude Code |