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 wxmb01/codex-app-autonomous-runs --skill timed-autonomous-rungit clone --depth 1 https://github.com/wxmb01/codex-app-autonomous-runsWrote 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/wxmb01/codex-app-autonomous-runs/timed-autonomous-run)<a href="https://agentmods.dev/skills/wxmb01/codex-app-autonomous-runs/timed-autonomous-run"><img src="https://agentmods.dev/badge/skills/wxmb01/codex-app-autonomous-runs/timed-autonomous-run/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/wxmb01/codex-app-autonomous-runs/timed-autonomous-run"><img src="https://agentmods.dev/badge/skills/wxmb01/codex-app-autonomous-runs/timed-autonomous-run.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 | $0.00069 | $0.06788 |
| Opus 5 | $0.00034 | $0.03394 |
| Sonnet 5 | $0.00014 | $0.01358 |
| Haiku 4.5 | $0.00007 | $0.00679 |
Grade A, and why
timed-autonomous-run 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 10d 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 — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Timed Autonomous Run
Use this skill to turn requests like "run this project for 2 hours", "auto-improve this project", "continue in the background", "key checkpoints only", or equivalent Chinese requests into Codex App automations.
If the user asks for Codex App-side no-pause, uninterrupted, no-idle, "not even one second of pause", 30-hour continuous work, or equivalent, do not rely on Codex App heartbeat automations as the primary execution mechanism. Heartbeat automations are timed wakeups, not permanent workers. Do not switch to CLI/local runner for this requirement.
For App-only uninterrupted requests, run as one long active Codex App work session: stay in the current thread, continue using tools, editing, validating, self-reviewing, and reporting progress until the requested duration expires, the goal is complete, or a human checkpoint is required. Do not send a final answer just because one step is done.
Core Policy
- Use Codex App automations directly when the task is compatible with scheduled wakeups.
- Exception: for explicit App-only no-pause or long continuous runs, use a long active App thread session, not heartbeat or CLI/local runner.
- Prefer one focused automation per project/task. Do not use one global heartbeat for every project.
- For short manual timed runs, use a thread heartbeat with the target path and stop count in the prompt.
- For recurring long-term maintenance, use a project/cron automation with
cwds; useexecutionEnvironment = "worktree"for Git repositories. - Before creating anything, check existing automations. Update a matching automation instead of creating a duplicate.
- If the target folder is missing, empty, or clearly not a project, ask for the real project path instead of creating a useless automation.
- A user request for a timed autonomous project run of 1 hour or more is explicit authorization to start read-only reviewer subagents for review work. Do not require separate wording such as "start a subagent" or "parallel agent" before using the required review lane.
- For 1 hour or longer App-only/timed project runs, launch the reviewer lane at the start of the run. If the target requires orientation first, do only the minimum path/git/stack/risk scan needed to write a useful reviewer prompt, then start the reviewer in that same first cycle before the first implementation edit.
What ships with it
7 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.
- 10d ago First seen · 598 lines · 69 tokens per session scan A e5c1f87adf29
timed-autonomous-run is a skill published in the GitHub repository wxmb01/codex-app-autonomous-runs (11 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 6,788 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.