OPOS: Skill for Claude Code

.claude/skills/unschedule-process/SKILL.md

unschedule-process is a skill for Claude Code from Koroqe/OPOS. It costs 42 tokens per session (1,329 once invoked), scanned A, original, MIT.

A procedure for stopping a scheduled automated process that runs through Claude Code’s cron system.

In plain words
What is it for?
It cancels cloud routines or removes scheduled GitHub Actions workflow files, depending on where the process runs.
Why use it?
It prevents a previously scheduled routine from running while preserving its schedule declaration for possible later reuse.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code.

This is Koroqe/OPOS's own configuration. It tells Claude Code how to work on OPOS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OPOS configures →

View source ↗ Koroqe/OPOS
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Koroqe/OPOS/main/.claude/skills/unschedule-process/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Koroqe/OPOS

Made for: Claude Code.

Wrote 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.

agentmods badge for unschedule-process

README.md
[![agentmods](https://agentmods.dev/badge/skills/koroqe/opos/unschedule-process.svg)](https://agentmods.dev/skills/koroqe/opos/unschedule-process)
Your own site
<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>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 688b96dbd97a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

.claude/skills/unschedule-process/SKILL.md · 66 lines

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 to CronList and matches by prompt prefix /<process-name>.

Steps

  1. Resolve repo root via git rev-parse --show-toplevel.

  2. Look up routine id (cache fast-path). Read .claude/scheduled-processes.json. Find the row where process_name == <input>. If found: take routine_id and proceed to step 4.

Read the full file on GitHub · 66 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 66 lines · 42 tokens per session scan A 688b96dbd97a

Subscribe to this mod's changes

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.