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/jacehwang/codex-usage-sidebar/manage-usage-sidebarnpx skills add JaceHwang/codex-usage-sidebar --skill manage-usage-sidebargit clone --depth 1 https://github.com/JaceHwang/codex-usage-sidebarWrote 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/skills/jacehwang/codex-usage-sidebar/manage-usage-sidebar)<a href="https://agentmods.dev/skills/jacehwang/codex-usage-sidebar/manage-usage-sidebar"><img src="https://agentmods.dev/badge/skills/jacehwang/codex-usage-sidebar/manage-usage-sidebar.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 | $0.00062 | $0.00499 |
| Opus 5 | $0.00031 | $0.00249 |
| Sonnet 5 | $0.00012 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
manage-usage-sidebar scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Manage Codex Usage Sidebar
Use the plugin control script. Keep the native companion outside the signed Codex application bundle so official upgrades cannot overwrite it.
Commands
- Install or refresh:
bash "$PLUGIN_ROOT/scripts/sidebar-control.sh" ensure --plugin-root "$PLUGIN_ROOT" --plugin-data "$PLUGIN_DATA" - Check:
bash "$PLUGIN_ROOT/scripts/sidebar-control.sh" status --plugin-root "$PLUGIN_ROOT" --plugin-data "$PLUGIN_DATA" - Repair:
bash "$PLUGIN_ROOT/scripts/sidebar-control.sh" repair --plugin-root "$PLUGIN_ROOT" --plugin-data "$PLUGIN_DATA" - Uninstall only when explicitly requested:
bash "$PLUGIN_ROOT/scripts/sidebar-control.sh" uninstall --plugin-root "$PLUGIN_ROOT" --plugin-data "$PLUGIN_DATA"
On Windows, use the PowerShell control script instead:
$control = Join-Path $env:PLUGIN_ROOT 'scripts\sidebar-control-windows.ps1'
powershell.exe -NoProfile -NonInteractive -ExecutionPolicy Bypass -File $control ensure -PluginRoot $env:PLUGIN_ROOT -PluginData $env:PLUGIN_DATA
powershell.exe -NoProfile -NonInteractive -ExecutionPolicy Bypass -File $control status -PluginRoot $env:PLUGIN_ROOT -PluginData $env:PLUGIN_DATA
The Windows status runtime=stopped reason=not-running means the installed companion is not
currently running; it is not a device-validation gate. Run ensure once, or restart Codex so the
SessionStart hook starts it automatically. A missing titlebar, unsupported UIA structure, or stale
Codex process is reported by the running companion's diagnostic state instead of blocking install.
After install or repair, tell the user that macOS may require one-time Accessibility permission for Codex Usage Sidebar. Never claim that permission was granted unless the operating system reports it.
For language reports, use the sanitized language= and language_source= fields from
status. process reflects Codex's effective displayed locale, including Auto; do not
request or expose raw process arguments.
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 · 42 lines · 62 tokens per session scan A e857b3edbcdf
manage-usage-sidebar is a skill published in the GitHub repository JaceHwang/codex-usage-sidebar (3 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 499 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
inbox-cleanup
Run a high-recall, multi-pass email inbox cleanup. Pattern-based subject queries catch 25x more archivable email than sender scans alone. Includes urgency triage, classification signals, and post-cleanup filter setup.
inbox-management
Ongoing Gmail inbox management via scheduled runs. Archives known noise, flags urgent items, drafts replies in-thread (never auto-sends), and catches stale follow-ups. Empty polls spend no model tokens. Starts in flag-only mode.
outlook
Manage Outlook email — drafting, sending, organizing, rules, vacation replies, and inbox analysis.
notifications
Send notifications through the unified notification router.