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 skills/etr/groundwork/statuslinenpx skills add etr/groundwork --skill statuslinegit clone --depth 1 https://github.com/etr/groundworkWhat 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 | $0.00016 | $0.00840 |
| Opus 5 | $0.00008 | $0.00420 |
| Sonnet 5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade B, and why
statusline scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. Read `$HOME/.claude/settings.json`, treating a missing file as `{}`. Inspect its `statusLine` value. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Before modifying any file, verify the renderer's hard dependencies. Run `command -v jq` and `command -v curl`. If either command is missing, stop and report which dependency must be installed. `gh` is optional and onl How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Groundwork Statusline
Configure Groundwork's optional statusline only after the user explicitly invokes this workflow.
Use the supplied action, install or uninstall. When no action is supplied, default to install. Reject any other action and show /groundwork:statusline [install|uninstall].
Install
The renderer asset is ${CLAUDE_PLUGIN_ROOT}/statusline-command.sh. Claude Code does not expand ${CLAUDE_PLUGIN_ROOT} inside a user statusLine command, and marketplace installs are versioned. Install a stable wrapper at $HOME/.claude/groundwork-statusline.sh so future plugin upgrades use the newest installed Groundwork plugin version.
-
Before modifying any file, verify the renderer's hard dependencies. Run
command -v jqandcommand -v curl. If either command is missing, stop and report which dependency must be installed.ghis optional and only adds pull-request information. -
Resolve the absolute home directory, the current plugin root, and the current plugin versions directory:
HOME_DIR="$HOME" PLUGIN_ROOT="$CLAUDE_PLUGIN_ROOT" VERSIONS_DIR="$(dirname "$CLAUDE_PLUGIN_ROOT")" -
Read
$HOME/.claude/settings.json, treating a missing file as{}. Inspect itsstatusLinevalue.- If it already invokes
$HOME/.claude/groundwork-statusline.sh, Groundwork owns it; continue so the wrapper is refreshed. - If a different
statusLineexists, ask the user before replacing it. Stop without modifying settings or the wrapper when they decline.
- If it already invokes
-
Write this executable wrapper, substituting the resolved absolute
<VERSIONS_DIR>and<PLUGIN_ROOT>:#!/usr/bin/env bash # Auto-generated by /groundwork:statusline. base="<VERSIONS_DIR>" fallback="<PLUGIN_ROOT>/statusline-command.sh" latest=$(ls -1 "$base" 2>/dev/null | grep -E '^[0-9]+\.[0-9]+\.[0-9]+$' | sort -t. -k1,1n -k2,2n -k3,3n | tail -1) script="$base/$latest/statusline-command.sh" if [ -n "$latest" ] && [ -f "$script" ]; then exec bash "$script" elif [ -f "$fallback" ]; then exec bash "$fallback" fi
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 69 lines · 16 tokens per session scan B 22e92c30cd54
statusline is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 21d ago), licensed MIT. It adds 16 tokens to every session and 840 once invoked, about $0.0001 per session on Opus 5. 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…