pulse-configuration

pulse-configuration is a skill for Claude Code from knqiufan/pulse-line. It costs 11 tokens per session (2,084 once invoked), scanned B, original, MIT.

A configuration guide for customizing pulse-line, a status bar that displays information during Claude Code sessions.

In plain words
What is it for?
Use it to configure model, context usage, Git, cost, duration, workspace, quota, rate-limit, and other supported status modules.
Why use it?
It explains where settings live and how to choose which status modules appear, in what order, and with which icons or theme.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the pulse-line plugin — 2 skills, 13 commands, 4 hooks shipped together

Good fit Use it to configure model, context usage, Git, cost, duration, workspace, quota, rate-limit, and other supported status modules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/knqiufan/pulse-line/pulse-configuration
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.

Any agent
npx skills add knqiufan/pulse-line --skill pulse-configuration
Clone the repo
git clone --depth 1 https://github.com/knqiufan/pulse-line

Made for: Claude Code.

Or install pulse-line, the plugin that ships this one along with the rest of its 2 skills, 13 commands, 4 hooks.

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 pulse-configuration

README.md
[![agentmods](https://agentmods.dev/badge/skills/knqiufan/pulse-line/pulse-configuration/github.svg)](https://agentmods.dev/skills/knqiufan/pulse-line/pulse-configuration)
Your own site
<a href="https://agentmods.dev/skills/knqiufan/pulse-line/pulse-configuration"><img src="https://agentmods.dev/badge/skills/knqiufan/pulse-line/pulse-configuration/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.

agentmods 80×15 button for pulse-configuration

Your own site · 80×15
<a href="https://agentmods.dev/skills/knqiufan/pulse-line/pulse-configuration"><img src="https://agentmods.dev/badge/skills/knqiufan/pulse-line/pulse-configuration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00011 $0.02084
Opus 5 $0.00005 $0.01042
Sonnet 5 $0.00002 $0.00417
Haiku 4.5 $0.00001 $0.00208

Measured 10d ago against content hash 15b7a9c51071, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

pulse-configuration scanned grade B with 1 finding 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 10d 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.

Example in `~/.claude/settings.json`:
skills/pulse-configuration/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pulse Configuration Skill

Overview

This skill provides guidance for configuring pulse-line modules and themes to customize the Claude Code status bar according to your workflow needs.

Configuration File

Location: ~/.claude/pulse/config.json

Open in editor:

pulse-line config

Module Configuration

Each module in the modules section has the following properties:

{
  "enabled": true,
  "order": 1,
  "icon": "[M]"
}

Available Modules

Core modules

model — current model; default tag [M].

context — usage bar; default [C].

git — branch plus /; default [G].

cost — USD total; default [$].

Advanced (config.json keys)

duration, workspace, turns, cacheRatio, thinking, rateLimits, weeklyQuota, mcpStatus, outputStyle — bracket tags [T][S] in defaults (see bundled pulse-config.ts).

accountUsage — Zhipu / DeepSeek quotas via merged settings*.json env + process.env. For Claude Code routed through ANTHROPIC_BASE_URL*.bigmodel.cn, GLM quotas use ANTHROPIC_AUTH_TOKEN (Anthropic-compat) when classic ZHIPU_* vars are absent.

thirdPartyApi — optional HTTP prefetch; rendered usage primarily via accountUsage cache.

iconSet

  • "text" (default): bracket labels + separators safe without Nerd Fonts.
  • "nerd": Nerd Font / Powerline symbols; patched terminal font required.

With iconSet: "text", if your config.json still has old Nerd/PUA characters in modules.*.icon or separator, Pulse replaces them with the bundled ASCII defaults so terminals without patched fonts do not show replacement glyphs (tofu).

Config files saved without schemaVersion run a one‑time upgrade first load (iconSet: nerd → text, then schemaVersion: 3 is written). Set iconSet to nerd again only if your terminal ships a patched Nerd Font.

Model name on the status bar

The model segment label resolves as follows (first non-empty wins):

Read the full file on GitHub · 268 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. 10d ago First seen · 268 lines · 11 tokens per session scan B 15b7a9c51071

Subscribe to this mod's changes

pulse-configuration is a skill published in the GitHub repository knqiufan/pulse-line (6 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 2,084 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.