Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dhruvil009/QuotaSentrynpx agentmods add commands/dhruvil009/quotasentry/quota-sentryWrote 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/dhruvil009/quotasentry/quota-sentry)<a href="https://agentmods.dev/commands/dhruvil009/quotasentry/quota-sentry"><img src="https://agentmods.dev/badge/commands/dhruvil009/quotasentry/quota-sentry/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/dhruvil009/quotasentry/quota-sentry"><img src="https://agentmods.dev/badge/commands/dhruvil009/quotasentry/quota-sentry.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 | $0.00014 | $0.00812 |
| Opus 5 | $0.00007 | $0.00406 |
| Sonnet 5 | $0.00003 | $0.00162 |
| Haiku 4.5 | $0.00001 | $0.00081 |
Grade A, and why
quota-sentry 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quota Sentry
The user invoked this command with: $ARGUMENTS
Instructions
Use this command to help the user manage Quota Sentry from the plugin root.
- Confirm
codexis available:
command -v codex
- If the user asks for status, run:
./scripts/quota-sentry status
- If the user asks to refresh quota state once, run:
./scripts/quota-sentry poll
- If the user asks to start monitoring, run:
./scripts/quota-sentry start
- If the user asks to stop monitoring, run:
./scripts/quota-sentry stop
- If the user asks to install enforcement, run:
./scripts/quota-sentry install-hook
After hook installation, tell the user to restart every running Codex process. Existing processes retain their loaded hook registry, and editing the hook file is not a reliable hot-reload mechanism.
- Weekly hard-blocking is already the default. If the user asks to change or explicitly persist its threshold, run:
./scripts/quota-sentry configure --weekly-mode hard-block --weekly-threshold-percent 99
If the user asks to opt out of weekly enforcement, run:
./scripts/quota-sentry configure --weekly-mode advisory
- If the user asks to run autonomous tests, run:
./scripts/autonomous-test
poll, start, and guard accept --source auto|codex-app-server|codexbar. Default auto uses only the authoritative Codex app-server and requires no CodexBar installation.
Weekly usage hard-blocks at 99% by default, even when no config file exists. configure --weekly-mode advisory is an explicit opt-out. Persisted policy lives in ~/.config/quota-sentry/config.json and does not require changing installed hook commands.
Quota policy follows window duration and canonical limit identity, not Codex's primary or secondary slot names. Short-term windows up to 24 hours use the normal guard; seven-day windows use weekly policy; unfamiliar long-term canonical windows block at 100%; durationless or canonically ambiguous data fails closed; auxiliary buckets remain advisory only when a canonical bucket is known.
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.
- 8d ago First seen · 91 lines · 14 tokens per session scan A 6bd3245c7c8c
quota-sentry is a command published in the GitHub repository dhruvil009/QuotaSentry (4 stars, last pushed 28d ago), licensed Apache-2.0. It adds 14 tokens to every session and 812 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 2026-08-31.
Other commands, from other repositories
do-it-retrospective
Reflect on an observed outcome and identify useful lessons.
arckit.customize
Copy plugin templates to project for customization.
arckit.search
Search across all project artifacts by keyword, document type, or requirement ID.
pu
Extract system improvements from content, monitor external sources, and scan bookmarks for upgrade opportunities. Shortcut for Upgrade skill (formerly PAIUpgrade).
3-review
Reviews a thread and gets it ready to finish.
experiment-development
Make a temporary markdown file in /experiments that includes.