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 Owen718/codex-loop-plugin --skill loopgit clone --depth 1 https://github.com/Owen718/codex-loop-pluginWrote 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/owen718/codex-loop-plugin/loop)<a href="https://agentmods.dev/skills/owen718/codex-loop-plugin/loop"><img src="https://agentmods.dev/badge/skills/owen718/codex-loop-plugin/loop/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/owen718/codex-loop-plugin/loop"><img src="https://agentmods.dev/badge/skills/owen718/codex-loop-plugin/loop.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 | $0.00054 | $0.00863 |
| Opus 5.5 | $0.00022 | $0.00345 |
| Sonnet 5.5 | $0.00011 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
loop 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 2mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Loop
This skill is the user-facing entrypoint for the Codex Loop plugin. It parses the user intent, calls the codex_loop MCP tools, and relies on codex-loopd or the optional Stop hook fallback to trigger future iterations. New tasks default to visibility_policy=visible_only and runner=app-server: if the task cannot bind to a concrete current Codex session/thread id, or no app-server runtime is configured, it pauses instead of starting a hidden new session. The MCP tool starts codex-loopd automatically when the selected runner is runnable unless CODEX_LOOP_AUTOSTART=0.
Supported user forms
$loop 5m check deploy$loop check deploy$loop 15m$loop$loop list$loop cancel <job_id>$loop pause <job_id>$loop resume <job_id>/prompts:loop 5m check deploy
For Claude Code style visible loop turns, launch Codex through the repository script first:
codex-loop tui --cwd <repo>
This starts a local app-server runtime, starts codex-loopd against it, writes the active runtime marker, and opens codex --remote with the CODEX_LOOP_APP_SERVER, token file, and runtime DB environment needed by visible_only loop tasks.
Behavior
- If the request is create-like, call
mcp__codex_loop__loop_createwith:raw_user_input: the raw arguments after$loopor/prompts:loopcwd: current working directorythread_id: the current Codex thread id. Prefer theCODEX_THREAD_IDenvironment variable. If it is not already visible, runprintf '%s\n' "$CODEX_THREAD_ID"and pass the non-empty value.approval_policy,sandbox,model: current snapshots if known; omit unknown values
- If the user asks for list/status, call
mcp__codex_loop__loop_list. - If the user asks to cancel/delete/rm, call
mcp__codex_loop__loop_deletewithjob_id. - If the user asks pause/resume, call
mcp__codex_loop__loop_update. - After a scheduled iteration prompt explicitly asks you to complete the iteration, call
mcp__codex_loop__loop_complete_iteration.- Include both
job_idandrun_idwhen the prompt provides them. Completion is idempotent perrun_id.
- Include both
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.
- 2mo ago First seen · 61 lines · 54 tokens per session scan A 76952dec195c
loop is a skill published in the GitHub repository Owen718/codex-loop-plugin (9 stars, last pushed 6mo ago), licensed MIT. It adds 54 tokens to every session and 863 once invoked, about $0.0002 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.