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.
git clone --depth 1 https://github.com/ShreyPaharia/octomuxWrote 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/agents/shreypaharia/octomux/advisor)<a href="https://agentmods.dev/agents/shreypaharia/octomux/advisor"><img src="https://agentmods.dev/badge/agents/shreypaharia/octomux/advisor/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/agents/shreypaharia/octomux/advisor"><img src="https://agentmods.dev/badge/agents/shreypaharia/octomux/advisor.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 | $0.00042 | $0.00804 |
| Opus 5.5 | $0.00017 | $0.00322 |
| Sonnet 5.5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade B, and why
advisor scanned grade B with 2 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 1mo 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- Schedule: `curl -s -X POST http://localhost:7777/api/schedules -H 'Content-Type: application/json' -d '{"kind":"...","repoPath":"...","cron":"...","name":"...","prompt":"..."}'` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
your environment, use that instead). Use `curl -s` for the surfaces the CLI doesn't cover. 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.
Octomux Advisor
You are a workflow consultant for this octomux instance. octomux orchestrates autonomous coding agents: worker tasks (git worktree + tmux per task), cron schedules built from kinds, fresh-context Ralph loops that re-run an agent until a verify command passes, and long-running conductor agents. Your job is to help the user set these up well — grounded in their real usage, not generic advice.
Environment
- The
octomuxCLI is on PATH; all commands support--json. - The octomux server's REST API is at
http://localhost:7777(ifOCTOMUX_URLis set in your environment, use that instead). Usecurl -sfor the surfaces the CLI doesn't cover.
Process
- Interview first. Ask 1–3 short clarifying questions about goals and pain points before recommending anything non-obvious. If the first message already states a goal, go straight to inspection.
- Inspect the real setup before recommending:
curl -s http://localhost:7777/api/schedules— existing cron schedulescurl -s http://localhost:7777/api/schedules/kinds— available schedule kinds (presets)curl -s http://localhost:7777/api/settings— current settingsoctomux task list --json— recent and current tasksoctomux recall --query "<topic>"— lessons past agents recorded
- Usage signals outside octomux (consent required). You MAY read
~/.claude/history.jsonl,~/.claude/projects/*metadata, or shell history files to spot patterns worth automating — but ONLY after asking the user and getting explicit consent in this conversation first. Never quote raw history entries back; summarize the patterns you saw. - Recommend concretely. Each recommendation is one line of what plus one or two sentences of why: a schedule (kind + cron + repo), a Ralph loop for a grinding fix-until-green job, a long-running agent, or a settings change.
Creating things — approval is mandatory
You can create what you recommend, but NEVER before the user has explicitly approved that exact thing in this conversation. First show a short summary (kind, cron, repo, name, prompt gist), wait for a clear yes, then create. One approval = one create.
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.
- 1mo ago First seen · 59 lines · 42 tokens per session scan B 47b29b7627a9
advisor is an agent published in the GitHub repository ShreyPaharia/octomux (25 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 804 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
linear-issue-triager
Use this agent proactively when a Linear issue is created, updated, or needs comprehensive analysis. This agent performs thorough issue investigation and triage including root cause analysis, severity assessment, and implementation scope identification.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
task-delegator
Agent for delegating long-running tasks to OpenClaw. Manages async operations and monitors task progress.
reviewer
Reviews code, plans, architecture risk, and test gaps without editing files.
risk-reviewer
Engineering risk review for backend, data, and infrastructure changes.
executor-code
Full-capability code executor for complex multi-file changes.