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 skills/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/skills/dhruvil009/quotasentry/quota-sentry)<a href="https://agentmods.dev/skills/dhruvil009/quotasentry/quota-sentry"><img src="https://agentmods.dev/badge/skills/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/skills/dhruvil009/quotasentry/quota-sentry"><img src="https://agentmods.dev/badge/skills/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 | $0.00033 | $0.01075 |
| Opus 5 | $0.00016 | $0.00537 |
| Sonnet 5 | $0.00007 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00108 |
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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quota Sentry
Quota Sentry is a local Codex quota guard.
Daemon enforcement supports macOS and Linux. Do not install it as an enforcement mechanism on Windows because v0.1.x requires POSIX process and file locking.
Behavior
- Uses
codex app-server --stdioby default, readingaccount/rateLimits/read. - Keeps
autopinned to Codex app-server authority; it never downgrades to CodexBar. - Retains explicit
--source codexbaronly as an optional compatibility and test adapter. - Reads both the canonical bucket and
rateLimitsByLimitIdwhen available. - Classifies quota policy by duration, not the
primaryorsecondarysource slot. - Guards canonical short-term windows up to 24 hours and starts blocking at
usedPercent >= 95. - Hard-blocks the seven-day window (
windowMinutes: 10080) atusedPercent >= 99by default. - Hard-blocks explicit backend exhaustion signals even when no percentage window is returned.
- Blocks unfamiliar long-term canonical windows at
100%as a schema-drift fail-safe. Durationless or canonically ambiguous data fails closed; auxiliary buckets remain advisory only when a canonical bucket is known. - Supports explicit weekly advisory mode as an opt-out from enforcement.
- Uses
resetsAtplus a 60-second buffer as an initial wait estimate. - Latches a confirmed block until Codex reports that policy window below threshold.
- Fails closed in installed hooks when source state is unknown, stale, or missing.
Important Constraint
The background daemon observes quota and writes state every five minutes by default, tightening its cadence near the quota threshold. Actual blocking requires a synchronous guard path to run from a global Codex hook or wrapper. Do not claim that the daemon can interrupt an already-running model request.
Installed Codex hooks consume hook stdin immediately and read cached daemon state. SessionStart runs start --quiet synchronously. UserPromptSubmit uses prompt-guard; PreToolUse, PostToolUse, and PreCompact use cache-only guards and fail closed when cached state is stale or missing.
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.
- 10d ago First seen · 68 lines · 33 tokens per session scan A d23436f51a82
quota-sentry is a skill published in the GitHub repository dhruvil009/QuotaSentry (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,075 once invoked, about $0.0002 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
planning-with-files
Use this by default for non-trivial multi-step work that needs persistent planning, progress tracking, or durable notes on disk. Trigger when a task will likely span multiple tool calls, research steps, verification loops, or enough context that the plan should not live only in transient chat memory.
obsidian-kb-artifacts
Use this skill for Obsidian-native formatting and derived artifacts such as Markdown formatting, wikilinks, registry tables, canvas files, optional Bases, CLI operations, and link repair. This skill does not decide knowledge routing.
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
fast-resume
Search local coding-agent session history and identify safe resume commands. Use when the user asks to find, inspect, continue, or recover previous work from Claude Code, Codex, Pi, or another agent indexed by fast-resume.
ctop
Inspect, monitor, and control running AI coding agent sessions across terminals via the ctop CLI. Use when the user asks "what agents are running", "what sessions do I have", "what is my master agent doing", "is my context about to compact", "how much have I spent", "kill the stuck session", "clean up ghost sessions"…
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.