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 skills add gokuafrica/claude-scheduler --skill skillgit clone --depth 1 https://github.com/gokuafrica/claude-schedulerWrote 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/gokuafrica/claude-scheduler/skill)<a href="https://agentmods.dev/skills/gokuafrica/claude-scheduler/skill"><img src="https://agentmods.dev/badge/skills/gokuafrica/claude-scheduler/skill/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/gokuafrica/claude-scheduler/skill"><img src="https://agentmods.dev/badge/skills/gokuafrica/claude-scheduler/skill.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 | $0.00135 | $0.02893 |
| Opus 5 | $0.00068 | $0.01447 |
| Sonnet 5 | $0.00027 | $0.00579 |
| Haiku 4.5 | $0.00014 | $0.00289 |
Grade A, and why
claude-scheduler scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash ~/.claude/scheduler/claude-scheduler.sh setup-notify --notify-command "curl" --notify-args "-d,{{message}},ntfy.sh/your-topic" How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Scheduler Management
Context
You are managing scheduled Claude Code jobs via the claude-scheduler CLI.
Platform Detection
First, determine the platform by checking uname:
- macOS:
unamereturns "Darwin" — use bash scripts with--kebab-caseflags - Windows: Running in PowerShell — use PowerShell scripts with
-PascalCaseflags
macOS
The management script is at:
~/.claude/scheduler/claude-scheduler.sh
Run commands via:
bash ~/.claude/scheduler/claude-scheduler.sh <command> [--flag value]
Windows
The management script is at:
$env:USERPROFILE\.claude\scheduler\claude-scheduler.ps1
Run commands via:
powershell -ExecutionPolicy Bypass -NoProfile -File "$USERPROFILE/.claude/scheduler/claude-scheduler.ps1" <command> [args]
Commands Reference
| Command | Purpose |
|---|---|
| create | Create a new scheduled job |
| update | Update an existing job |
| list | Show all jobs with status |
| enable | Re-enable a disabled job |
| disable | Temporarily pause a job |
| run | Execute a job immediately |
| delete | Permanently remove a job and its logs |
| logs | View latest log output |
| purge-logs | Delete old log files |
| status | Detailed job information |
| setup-notify | Configure failure notifications |
| test-notify | Send a test notification |
Parameter Syntax (macOS vs Windows)
macOS (--kebab-case) |
Windows (-PascalCase) |
Description |
|---|---|---|
--name |
-Name |
Job name (required for most commands) |
--prompt |
-Prompt |
The prompt Claude will execute |
--schedule |
-Schedule |
When to run (see schedule syntax) |
--description |
-Description |
Human-readable description |
--model |
-Model |
Claude model: sonnet, opus, haiku |
--max-budget |
-MaxBudget |
Max USD per run |
--effort |
-Effort |
low, medium, or high |
--work-dir |
-WorkDir |
Working directory (~ = home) |
--allowed-tools |
-AllowedTools |
Restrict to specific tools (comma-separated) |
--disallowed-tools |
-DisallowedTools |
Block specific tools (comma-separated) |
--log-retention |
-LogRetention |
Days to keep logs (default: 30) |
--append-system-prompt |
-AppendSystemPrompt |
Extra system prompt text |
--background |
-Background |
Run in background |
--keep-logs |
-KeepLogs |
Preserve logs on delete |
--tail |
-Tail |
Lines to show from log |
--days |
-Days |
Days threshold for purge-logs |
--notify-command |
-NotifyCommand |
Notification command |
--notify-args |
-NotifyArgs |
Notification arguments (comma-separated) |
--notify-on |
-NotifyOn |
Event types to notify on |
--disable |
-Disable |
Disable notifications |
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.
- 11d ago First seen · 295 lines · 135 tokens per session scan A cd408f13949c
claude-scheduler is a skill published in the GitHub repository gokuafrica/claude-scheduler (5 stars, last pushed 6mo ago), licensed MIT. It adds 135 tokens to every session and 2,893 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
relay
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…
agent-tamagotchi
Terminal pet that lives in your statusline. 12 species, 5 stats (DEBUGGING, PATIENCE, CHAOS, WISDOM, SPEED). Reacts to your workflow - happy when tests pass, sad when builds fail, excited during swarm mode. Deterministic species from user ID.