Borrowing it
Nothing to install: this file belongs to Koroqe/OPOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Koroqe/OPOS/main/.claude/skills/unschedule-process/SKILL.mdgit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/unschedule-process)<a href="https://agentmods.dev/skills/koroqe/opos/unschedule-process"><img src="https://agentmods.dev/badge/skills/koroqe/opos/unschedule-process.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 5.1 | $0.00042 | $0.01329 |
| Opus 5 | $0.00021 | $0.00665 |
| Sonnet 5 | $0.00008 | $0.00266 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
unschedule-process 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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unschedule-process
When to use
When the user wants to stop a previously-scheduled process from firing. Invoke as /unschedule-process <process-name>.
The skill wraps Claude Code's built-in CronDelete tool. It does NOT edit the source PROCESS.md's scheduling frontmatter — the declaration remains in place so the user can re-schedule later by re-running /schedule-process. To permanently retire the schedule, the user manually removes the 4 scheduling fields from PROCESS.md after unscheduling.
runtime: cloud branch (v0.14): cloud routines cannot be deleted via the API — unscheduling disables them: RemoteTrigger {action: "update", trigger_id: <from the cache row's cloud:prefix, or matched by nameopos-via{action: "list"}>, body: {"enabled": false}}. Remove the cache row and tell the user that permanent deletion is done by them at https://claude.ai/code/routines. Re-scheduling later re-enables in place (/schedule-process step 4b's idempotency path).
runtime: gha branch (v0.10): for a process whose cache row (or workflow-file presence) shows the GHA runtime, unscheduling = delete .github/workflows/opos-<process-name>.yml and commit the deletion (chore(core): unregister opos-<name> gha workflow) — a sensitive-path change, confirmed with the user. CronDelete is not involved. Mixed states (both a workflow file and a live CronCreate routine) → remove both, noting the one-driver rule was violated.
Prerequisite: same as schedule-process — the user must be logged into Claude Code (claude login).
Inputs
process-name— kebab-case name of the previously-scheduled process. The skill first looks up the routine id in the local cache.claude/scheduled-processes.json; if not found (e.g., on a fresh machine where the cache hasn't been seeded), it falls back toCronListand matches by prompt prefix/<process-name>.
Steps
-
Resolve repo root via
git rev-parse --show-toplevel. -
Look up routine id (cache fast-path). Read
.claude/scheduled-processes.json. Find the row whereprocess_name == <input>. If found: takeroutine_idand proceed to step 4.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 66 lines · 42 tokens per session scan A 688b96dbd97a
unschedule-process is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 1,329 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
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
task-queue
Persistent JSON-backed job queue for scheduling shell commands without raw cron — supports one-shot (run at a time) and recurring (cron schedule) tasks. Use when asked to schedule or run a job at/every some interval, list or cancel queued tasks, or check task status.
scheduler
Natural language task scheduling for Kite. Create, list, and cancel scheduled jobs in plain English with a human-readable registry of what's running and why.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
wp-content-workflows
This skill should be used when the user asks about "workflow automation", "triggers", "scheduled tasks", "WP-Cron", "content publishing triggers", "hook-based actions", "post status transitions", "automated notifications", "workflow triggers", "event-driven actions", "content lifecycle hooks", "multi-channel actions"…