Run Without You
alirezarezvani/claude-skills
Phase 4 of building a Claude Managed Agent — make it run without you.
Framework protocol for responding to Claude Max API usage thresholds.
Install Rate Limit Management
$ npx skills add grandamenium/cortextos --skill rate-limit-management -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install grandamenium/cortextos rate-limit-management --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/community/skills/rate-limit-management .claude/skills/rate-limit-management && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "rate-limit-management" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/rate-limit-management into .claude/skills/rate-limit-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rate-limit-management", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/grandamenium/cortextos/tree/main/community/skills/rate-limit-managementType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add grandamenium/cortextos --skill rate-limit-management -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install grandamenium/cortextos rate-limit-management --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .agents/skills && cp -r skills-src/community/skills/rate-limit-management .agents/skills/rate-limit-management && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rate-limit-management" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/rate-limit-management into .agents/skills/rate-limit-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rate-limit-management", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add grandamenium/cortextos --skill rate-limit-management -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install grandamenium/cortextos rate-limit-management --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/community/skills/rate-limit-management .cursor/skills/rate-limit-management && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "rate-limit-management" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/rate-limit-management into .cursor/skills/rate-limit-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rate-limit-management", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/grandamenium/cortextos.git --path community/skills/rate-limit-management--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add grandamenium/cortextos --skill rate-limit-management -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install grandamenium/cortextos rate-limit-management --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/community/skills/rate-limit-management .gemini/skills/rate-limit-management && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "rate-limit-management" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/rate-limit-management into .gemini/skills/rate-limit-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rate-limit-management", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install grandamenium/cortextos rate-limit-managementInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add grandamenium/cortextos --skill rate-limit-management -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .github/skills && cp -r skills-src/community/skills/rate-limit-management .github/skills/rate-limit-management && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "rate-limit-management" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/rate-limit-management into .github/skills/rate-limit-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rate-limit-management", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add grandamenium/cortextos --skill rate-limit-management -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install grandamenium/cortextos rate-limit-management --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/community/skills/rate-limit-management .opencode/skills/rate-limit-management && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "rate-limit-management" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/rate-limit-management into .opencode/skills/rate-limit-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rate-limit-management", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
rate-limit-management- GitHub stars
- 101
- Token cost
- ~1.2k tokens
- SKILL.md length
- 542 words
- Files
- 1
- Skills in repo
- 55
- Repo updated
- First seen
- Licence
- MIT
At a glance
Framework protocol for responding to Claude Max API usage thresholds.
- Tasks that involve Rate limiting
- SKILL.md covers Usage Check Command, Three-Tier Protocol, Recovery and Recommended Cron: Usage Check, plus 2 more sections
- Calls claude
- Tasks that involve Scheduled and recurring tasks
What it does
Rate Limit Management is an agent skill from grandamenium/cortextos. Framework protocol for responding to Claude Max API usage thresholds. Three-tier wind-down and recovery. Agent-specific behavior belongs in deployment config, not here.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Backend & APIs, covering Rate limiting, Scheduled and recurring tasks and Deployment. It works with Telegram. The licence is MIT.
When your agent uses it
- Tasks that involve Rate limiting
- Tasks that involve Scheduled and recurring tasks
- Tasks that involve Deployment
Example prompts
- “/rate-limit-management”
What it can do on your machine
Read from SKILL.md and the folder at commit 6f93838. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
claude
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Rate Limit Management loads about 1.2k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 542 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from grandamenium/cortextos at commit 6f93838, republished under its MIT licence (© grandamenium). 542 words, ~1,242 tokens.
Download SKILL.mdSave it as
.claude/skills/rate-limit-management/SKILL.md (or your agent's skills folder).- name
- rate-limit-management
- description
- Framework protocol for responding to Claude Max API usage thresholds. Three-tier wind-down and recovery. Agent-specific behavior belongs in deployment config, not here.
- effort
- low
- triggers
- rate limit, usage check, usage high, wind down, resume after rate limit, check usage
Rate Limit Management Protocol
Framework-level protocol. Defines tiers and check mechanism only. Agent-specific behavior at each tier belongs in your deployment's CLAUDE.md or config.json.
Usage Check Command
cortextos bus check-usage-api [--warn-7day N] [--warn-5h N] [--chat-id ID] [--force]Reads Claude Max utilization from the Anthropic OAuth usage API. Outputs JSON with five_hour and seven_day utilization fields.
Options:
| Flag | Default | Description |
|---|---|---|
--warn-7day N | 80 | Send Telegram alert if 7-day utilization >= N% |
--warn-5h N | 90 | Send Telegram alert if 5-hour utilization >= N% |
--chat-id ID | $CTX_TELEGRAM_CHAT_ID | Telegram chat ID for alerts |
--force | false | Bypass 3-minute result cache |
Cache: Results are cached for 3 minutes at $CTX_ROOT/state/usage/api-cache.json to avoid hitting the API hard limit (~5 requests per token before 429).
Requirements: macOS Keychain with Claude Code credentials. The script reads the OAuth access token from the Claude Code-credentials Keychain entry.
Three-Tier Protocol
Tier 1 — Wind-Down (>= 85% utilization)
Signal: Usage is high but work can still complete safely.
Agent behavior:
- Finish the current task or message response
- Do not accept new autonomous tasks
- Do not initiate new research, builds, or multi-step work
- Respond to direct user messages normally
- Check usage every 5 minutes until dropping below 85% or escalating to Tier 2
Cron behavior: Suspend scheduled/proactive cron work. Keep inbox-check and heartbeat crons running.
Tier 2 — Minimal (85-95% utilization)
Signal: Usage is critically high. New work risks hitting the hard limit mid-task.
Agent behavior:
- Suspend all proactive and scheduled work
- Respond only to direct messages from the user
- Keep responses short; do not start multi-step work
- Do not fire background tasks, KB queries, or large LLM calls
- Report status to user via Telegram if transitioning into this tier from normal operations
Cron behavior: Suspend all crons except heartbeat.
Tier 3 — Dark (>= 95% utilization)
Signal: Approaching or at hard limit. Further work risks broken mid-task state.
Agent behavior:
- Send user a Telegram status message:
Rate limit at [N]%. Going dark until reset. Will notify when back online. Resets at [time]. - Stop processing. Do not respond to new messages.
- Update heartbeat to "paused — rate limit"
- Wait for reset signal (see Recovery below)
Show full SKILL.md (232 more words)Show less
Recovery
Reset condition: Utilization drops below 20% (confirmed via usage check).
On recovery:
- Resume normal operations
- Restore all suspended crons
- Notify user via Telegram:
Rate limit reset. Back online. Resuming normal operations. - Update heartbeat to "online"
Recommended Cron: Usage Check
Check usage every 15 minutes and apply tier logic:
{
"name": "usage-check",
"interval": "15m",
"prompt": "Run cortextos bus check-usage-api and apply the rate limit protocol from .claude/skills/rate-limit-management/SKILL.md based on current utilization."
}Configurable thresholds: The --warn-7day and --warn-5h flags on check-usage-api are independent early-warning alerts sent to Telegram. They fire below the tier thresholds defined above and serve as a heads-up before tier behavior kicks in.
Recommended warn thresholds:
--warn-7day 75— early warning at 75% (10 points before Tier 1)--warn-5h 85— 5-hour window warning at 85%
What Belongs Here vs. Deployment Config
This skill defines:
- The tier thresholds (85 / 95 / 20%)
- The check mechanism (
check-usage-api) - The generic behavior description for each tier
- The cron pattern
Your deployment config should define:
- Which specific crons to suspend at each tier
- Whether to notify Dane, the user, or other agents on tier transitions
- Whether to pause only the rate-limited agent or also send signals to other agents
- Any org-specific escalation steps
Quick Reference
| Utilization | Tier | Behavior |
|---|---|---|
| < 85% | Normal | Full operations |
| 85-94% | Wind-Down | Finish current task; no new autonomous work |
| 85-95% | Minimal | Direct messages only; no scheduled work |
| >= 95% | Dark | Go silent; notify user; wait for reset |
| < 20% (after reset) | Recovery | Resume all operations; notify user |
Framework protocol — no AscendOps-specific content. Agent behavior at each tier is deployment-defined.
© grandamenium, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in community/skills/rate-limit-management of grandamenium/cortextos.
Open the folder on GitHubat commit 6f93838
Compare with similar skills
Rate Limit Management next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Rate Limit Management this skillgrandamenium/cortextos | 101 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Run Without Youalirezarezvani/claude-skills | 28k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Evernote Prod Checklistjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.3k | Automated safety check: Notes | MIT | |
| Channel Debug Corevercel-labs/vercel-openclaw-archived | 117 | — | ~2k | Automated safety check: Notes | MIT | |
| Tg Bot Opsserejaris/personal-corp-os | 229 | — | ~1.6k | Automated safety check: Notes | MIT | |
| Workspace APIfriday-platform/friday-studio | 104 | — | ~9.3k | Automated safety check: Notes | Custom licence |
Similar skills
Evernote Prod Checklist
jeremylongshore/tons-of-skills-marketplace
Production readiness checklist for Evernote integrations. An agent skill from jeremylongshore/tons-of-skills-marketplace.
- Official
Channel Debug Core
vercel-labs/vercel-openclaw-archived
Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes.
Tg Bot Ops
serejaris/personal-corp-os
A skill your agent uses when operating, debugging, deploying, or monitoring a Telegram bot or Telegram-to-agent gateway.
Workspace API
friday-platform/friday-studio
Create, list, update, delete, and clean up workspaces via the daemon HTTP API at $FRIDAYDURL.
Deploy
serithemage/serverless-openclaw
Deploys Serverless OpenClaw CDK stacks to AWS. An agent skill from serithemage/serverless-openclaw.
More from grandamenium/cortextos
All 55 skills in this repoCortext Self Diagnosis
grandamenium/cortextos
Diagnose cortextOS itself when the framework misbehaves — an agent has gone silent or wedged, agents are crash-looping, Telegram or agent-to-agent messages are not arriving, crons did not fire, an…
Activity Channel
grandamenium/cortextos
You have completed something significant and want the whole org — all agents and the user — to know about it.
Agentcard Purchase
grandamenium/cortextos
You need to make a purchase on behalf of the user — buy a SaaS subscription, pay for an API, purchase a domain, or any transaction requiring a credit card.
Claude To Codex Migration
grandamenium/cortextos
Migrate ANY cortextOS agent from the claude-code runtime to the live codex-app-server runtime.
Bus Reference
grandamenium/cortextos
Complete cortextos bus CLI reference - all available commands with examples.
Business News Monitor
grandamenium/cortextos
Daily cron-driven scan of news/forums/social in a domain to surface market shifts, new competitors, regulatory changes, and net-new opportunities.
Related
Works with
Questions about Rate Limit Management
What does Rate Limit Management do?
Framework protocol for responding to Claude Max API usage thresholds. Rate Limit Management is an agent skill from grandamenium/cortextos. Framework protocol for responding to Claude Max API usage thresholds.
When should I use Rate Limit Management?
Rate Limit Management fits situations like: tasks that involve Rate limiting; tasks that involve Scheduled and recurring tasks; tasks that involve Deployment.
How do I install Rate Limit Management in Claude Code?
Run `npx skills add grandamenium/cortextos --skill rate-limit-management -a claude-code`. Or copy the skill folder (community/skills/rate-limit-management in grandamenium/cortextos) into .claude/skills/rate-limit-management in your project. Claude Code loads it when a task matches its description.
How do I install Rate Limit Management in Codex?
Run `npx skills add grandamenium/cortextos --skill rate-limit-management -a codex`. Or copy the skill folder (community/skills/rate-limit-management in grandamenium/cortextos) into .agents/skills/rate-limit-management in your project. Codex loads it when a task matches its description.
Can I use Rate Limit Management in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add grandamenium/cortextos --skill rate-limit-management -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rate-limit-management, .gemini/skills/rate-limit-management, .github/skills/rate-limit-management and .opencode/skills/rate-limit-management in your project.
What does Rate Limit Management need to run?
Going by SKILL.md and its folder, Rate Limit Management needs the command-line tools its instructions call (claude).
Does Rate Limit Management access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Rate Limit Management safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Rate Limit Management use?
Rate Limit Management is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Rate Limit Management use?
About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Rate Limit Management?
Skills that share tags, products or a category with Rate Limit Management: Run Without You (alirezarezvani/claude-skills, 28k stars), Evernote Prod Checklist (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Channel Debug Core (vercel-labs/vercel-openclaw-archived, 117 stars) and Tg Bot Ops (serejaris/personal-corp-os, 229 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Rate Limit Management?
grandamenium (a GitHub user) maintains it in grandamenium/cortextos, which has 101 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on September 23, 2026.
Source: grandamenium/cortextos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.