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 commands/nycu-chung/cc-statusline/rowsgit clone --depth 1 https://github.com/NYCU-Chung/cc-statuslineWrote 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/nycu-chung/cc-statusline/rows)<a href="https://agentmods.dev/commands/nycu-chung/cc-statusline/rows"><img src="https://agentmods.dev/badge/commands/nycu-chung/cc-statusline/rows.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 | $0.00014 | $0.01210 |
| Opus 5 | $0.00007 | $0.00605 |
| Sonnet 5 | $0.00003 | $0.00242 |
| Haiku 4.5 | $0.00001 | $0.00121 |
Grade A, and why
rows 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cc-statusline :: row configuration
Manage cc-statusline. Config lives at ~/.claude/cc-statusline-rows.json; statusline.js reads it on every render.
A top-level enabled flag acts as the master switch — when enabled: false, the statusline prints nothing at all. Individual row flags control which sections appear when the statusline IS enabled.
Special configuration options
Besides row toggles the file also holds non-row behaviour knobs:
| key | type | default | description |
|---|---|---|---|
enabled |
boolean | true |
Master switch — false = no output at all |
summaryInterval |
number | 10 |
How many UserPromptSubmit events between session-summary nudges (minimum 1) |
aggWindowDays |
number | 0 |
Rolling window (in days) for the all-session cost + tokens aggregate. Default 0 = all time. Set to 7 / 30 / 90 etc. for a rolling view. |
statuslineWidth |
number | (auto) | Hard-set the box width in columns. Width auto-detection is unreliable inside the statusline hook (see #5430) — Claude Code doesn't pass the available width and most fallbacks return wrong values. Measure your terminal once (tput cols from a normal shell) and set it here. Default fallback is 120. |
statuslineWidthOffset |
number | 4 |
Columns reserved on the right after statuslineWidth is resolved, to leave room for Claude Code's own padding/indicator. Increase if the box still gets truncated; decrease to 0 if your terminal renders edge-to-edge. |
Valid row keys
| key | what it controls |
|---|---|
summary |
Top session-summary row (auto-written by Claude) |
dir |
📁 directory + +added -removed lines |
repo |
owner/repo branch (N changed) row |
model |
Model name + effort level |
duration |
Active session time (sum of turn durations from UserPromptSubmit → Stop, idle outside turns naturally excluded). Shares the model row area visually but toggles independently. |
cost |
cost $TOTAL (<window>) · $SESSION (this session) — window label reflects aggWindowDays |
usage |
tokens ... context ... compact ... row |
quota |
5h-quota + 7d-quota row with countdowns |
agents |
Subagent activity row |
memory_mcp |
Combined memory │ mcp row |
edited |
Recently edited files row |
history |
Right-side message history column |
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 · 71 lines · 0 tokens per session scan A c9dad9f04838
rows is a command published in the GitHub repository NYCU-Chung/cc-statusline (264 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 1,210 once invoked, about $0.0001 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 commands, from other repositories
publish
Publish repository to GitHub with full setup.
release
Create a GitHub release with auto-generated changelog.
prime
Load project context and output a structured summary.
ultrathink
Append the ultrathink instruction.
open
Build the current project's claude-telemetry dashboard, then open it in the browser.
autobot
Launch a bot command in an isolated autobot session with its own worktree, backend, and frontend.