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 agentmods add skills/gaelic-ghost/socket/schedule-agent-worknpx skills add gaelic-ghost/socket --skill schedule-agent-workgit clone --depth 1 https://github.com/gaelic-ghost/socketWhat 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 | $0.00053 | $0.00616 |
| Opus 5 | $0.00026 | $0.00308 |
| Sonnet 5 | $0.00011 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
schedule-agent-work 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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schedule Agent Work
Choose scheduling only after the work has a bounded input, write scope, validation, escalation boundary, and result-delivery route.
Choose The Smallest Durable Shape
- Use an in-run worker for a short dependency-free result the coordinator needs before continuing.
- Use a native scheduled task for periodic or trigger-based work where the host can show status and deliver a result to Gale.
- Use CI or
codex execfor deterministic repository jobs with structured output and explicit sandboxing. - Use a queue or board for retries, dependencies, multiple roles, durable comments, artifacts, or human decisions.
- Use an application service only when application code must own state, tools, approvals, tracing, and deployment.
Required Schedule Contract
Define the trigger/cadence, owner, input snapshot, write authority, idempotency or duplicate policy, timeout/retry limit, no-op/rollback behavior, escalation trigger, status surface, artifact retention, and route that delivers the final report to Gale and the coordinator.
Deferred Remote Work
When an agent reaches an external CI, review, release, deployment, or provider gate, use a host-native future wakeup rather than leaving a terminal, watcher, or polling loop alive. Schedule every agent-created recheck at least five minutes after the observation that caused it. A shorter operation is allowed only for one bounded, command-local re-read; it must not become a repeated polling loop.
For Codex desktop or ChatGPT, create or reuse a same-thread heartbeat through
the host automation surface. For Hermes, create or update the same
self-contained cronjob with deliver="origin" and attach_to_session=true;
confirm the cron tool and gateway are active first. Before scheduling, inspect
for an active continuation with the same target and gate. If it remains pending
without failure or identity drift, leave that scheduler item in place rather
than deleting and recreating it. Pause or delete it only once the gate clears,
fails, is cancelled, or changes identity. The continuation must carry the exact
target, observed state, closed gate, earliest recheck time, and safe next
command. It must re-read source-of-truth state before it performs any mutation.
What ships with it
1 file 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.
- 2d ago First seen · 59 lines · 53 tokens per session scan A 2230833b02b6
schedule-agent-work is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 53 tokens to every session and 616 once invoked, about $0.0003 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
xcode-disk-cleanup
Audit and safely clean Xcode-related developer storage on macOS. Use whenever a developer mentions low disk space, Xcode storage, DerivedData, simulator devices or runtimes, stale beta platforms in Xcode Settings, DeviceSupport, archives, dSYMs, CocoaPods caches, simulator dyld caches, project .build folders…
storescreens
Set up and run storescreens-cli to automate App Store screenshot capture for iOS apps: render captioned/framed App Store-ready screenshots with device bezels, markdown captions, and panoramic backgrounds; upload screenshots + per-locale metadata (name, subtitle, description, keywords, what's new, promotional text) to…
poll-github-work
Poll and rank open GitHub issues, RFCs, and pull requests for maintainer work, or start one explicitly selected item. Use when a user asks what to work on, requests backlog priorities, says "poll work," wants actionable issues or pull requests, or says "start.
test
Run tests. Use after code changes to validate. Arguments: unit (default, no GPU), e2e (with models), filter name, or all.
release
Build, sign, notarize, and publish a new DroidProxy release. Use when the user wants to cut a release, merge a PR and ship it, or asks to build/notarize/publish. Covers the full pipeline: PR merge, version bump, swift build, code signing, Apple notarization, Sparkle appcast update, and GitHub release creation.
remarc
Manage Remarc session comments and contextual feedback. Use when the user mentions Remarc sessions, comments, handoff, triage, review, addressing, resolving, status updates, or summaries.