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/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/statusline-help)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/statusline-help"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/statusline-help/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/atretyak1985/swarmery/statusline-help"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/statusline-help.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 | $0.00022 | $0.02086 |
| Opus 5 | $0.00011 | $0.01043 |
| Sonnet 5 | $0.00004 | $0.00417 |
| Haiku 4.5 | $0.00002 | $0.00209 |
Grade A, and why
statusline-help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/statusline-help — Decode the custom statusline
Print a clear reference for the custom statusline rendered at the bottom of the
terminal. Script: .claude/statusline/statusline.sh in consumer projects
(an opt-in deploy — swarmery onboard/attach --statusline-src … or a manual
copy, see docs/ONBOARDING.md "Statusline"; wired via the statusLine key in
.claude/settings.json); source of truth lives at plugins/core/statusline/.
Steps
-
Render a live sample so the user sees current colors and values. Run:
SL="$CLAUDE_PROJECT_DIR/.claude/statusline/statusline.sh" [ -f "$SL" ] || SL="$CLAUDE_PROJECT_DIR/plugins/core/statusline/statusline.sh" printf '%s' '{"version":"2.1.170","model":{"id":"claude-opus-5[1m]","display_name":"Opus 5 (1M context)"},"output_style":{"name":"Explanatory"},"workspace":{"current_dir":"'"$CLAUDE_PROJECT_DIR"'","project_dir":"'"$CLAUDE_PROJECT_DIR"'"},"cwd":"'"$CLAUDE_PROJECT_DIR"'","context_window":{"used_percentage":15},"rate_limits":{"five_hour":{"used_percentage":8,"resets_at":2000000000},"seven_day":{"used_percentage":20,"resets_at":2000600000}},"cost":{"total_cost_usd":5.04,"total_duration_ms":2792000,"total_lines_added":299,"total_lines_removed":6}}' | bash "$SL"(This is a synthetic payload for illustration — the real statusline uses the live session's values.)
-
Present this reference table verbatim:
| Line | Field | Meaning | Source |
|---|---|---|---|
| 1 Header | AGENTS_STATUSLINE |
Header title. Opt-in: with SWARMERY_STATUSLINE_USER=1 it's replaced by the email of the subscription this session runs under |
.oauthAccount.emailAddress from the session's .claude.json ($CLAUDE_CONFIG_DIR/.claude.json if set, else ~/.claude.json) — no network |
Model · Style |
Active model + output style | JSON .model.display_name, .output_style.name |
|
| 2 LOC | City |
Weather location (default from the script) | SWARMERY_STATUSLINE_LOC env → wttr.in |
HH:MM |
Local clock | recomputed each render | |
+28°C Sunny |
Weather | wttr.in, cached 10m, background refresh | |
| 3 ENV | CC <ver> |
Claude Code version | JSON .version |
AG/SK/CMD/Hooks |
Fleet counts (agents/skills/commands/hooks) | find under .claude/ (matches SessionStart banner) |
|
| 4 CONTEXT | bar + % |
Context window fill | JSON .context_window.used_percentage (fallback: transcript). Green <50 · yellow ≥50 · red ≥80 |
| 5 USAGE | 5H <pct>% ⟳<reset> |
Official 5-hour plan limit used + reset countdown | JSON .rate_limits.five_hour (same as /usage) |
WK <pct>% ⟳<reset> |
Weekly plan limit used + reset | JSON .rate_limits.seven_day |
|
FB <pct>% ⟳<reset> |
Fable-5 weekly window (the "Fable" bar on claude.ai settings→usage). Opt-in, hidden by default | fetch-fable-usage.sh → GET /api/oauth/usage (OAuth token from the macOS Keychain item of the session's config dir — CLAUDE_CONFIG_DIR-aware, multi-subscription-safe), cached per account, background refresh |
|
| 6 SESSION | $cost |
This session's spend | JSON .cost.total_cost_usd |
+N/-N |
Lines added / removed | JSON .cost.total_lines_added/removed |
|
⏱ <dur> |
Session duration | JSON .cost.total_duration_ms |
|
| 7 PWD | dir |
Current folder | JSON .workspace.current_dir |
Branch/Age/Mod/Sync |
Git branch · time since last commit · dirty count · ahead/behind. Vanishes outside a git repo. | git against cwd |
|
| 8 MEMORY | Memories/Tasks/Sessions |
Memory files · active task dirs · recorded sessions | filesystem under memory/, the workspace working/ tree (legacy: .claude-workspace/working/), the sessions dir |
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.
- 6d ago First seen · 120 lines · 22 tokens per session scan A 8e3c0907c446
statusline-help is a command published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 2,086 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 2026-09-03.
Other commands, from other repositories
gws-chat
Send messages and manage Google Chat spaces.
gws-people
Search and look up Google Contacts and directory profiles.
gws-keep
List and read Google Keep notes.
meeting-prep
Prepare for your next meeting with agenda and attendees.
standup
Generate a standup report from Google Workspace data.
agenda
Show upcoming calendar events.