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 ShreyPaharia/octomux --skill learngit 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/skills/shreypaharia/octomux/learn)<a href="https://agentmods.dev/skills/shreypaharia/octomux/learn"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/learn/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/shreypaharia/octomux/learn"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00875 |
| Opus 5 | $0.00027 | $0.00438 |
| Sonnet 5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
learn 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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record a learning
Save a durable, evidenced lesson for future runs on this repo/task via the octomux learn CLI.
There is no per-add human gate — what you write here goes straight into the pool that gets
seeded into future prompts, so the bar is on you.
When to use
- You just fixed something that wasn't obvious from the code alone (a flaky mock, a required env var, a gotcha in a build step, a convention you only found by trial and error).
- You're about to end your turn and you have context (your reasoning, not just the outcome) that the transcript will not carry forward — the next fresh-context iteration only sees the prompt, not your chain of thought.
The schema
octomux learn --trigger "<when this applies>" --lesson "<the durable fact or action>" \
--evidence "<file / command / error that proves it>" [--private]
--trigger— the situation this applies to (so a future run knows when to recall it).--lesson— the durable fact or action itself. State it as something actionable, not a vague reminder.--evidence— the file path, command, or error text that backs it up. No evidence, no save — if you can't point at something concrete, it isn't a learning yet, it's a guess.--private— use for a quirk specific to this job (a one-off env, a task-specific workaround). Omit it (shared, repo-general) for anything a different task in this repo would also benefit from.
The bar: save the why, not just the what
The transcript is gone once your context resets. The lesson is your only chance to hand your reasoning forward — write it like you're leaving a note for an agent with none of your context.
Good (durable, evidenced, actionable):
- "When
bun testhangs onlaunch.test.ts, the fs mock needsdefault: mocked— server/task-engine/setup" - "The hedging retry lives in server/retry.ts; jitter was missing and caused thundering-herd retries under load — server/retry.ts:42"
Bad (vague, no evidence, not a lesson):
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.
- 11d ago First seen · 77 lines · 54 tokens per session scan A 37c8abbb8b00
learn is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 875 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 2026-08-30.
Other skills, from other repositories
orcast
Use when orchestrating multiple agents in Orca: fan out parallel workers, pipeline work across stages, adversarially verify findings, run judge panels or loop-until-dry sweeps, or delegate a task and get the result back. You write a Plan definition in real JavaScript — a worker-workflow graph of worker, action, and…
muster
Coordinate with other coding-agent sessions — any machine, any vendor — on this repo via the muster CLI. Use when the user says /muster, asks to join or check a fleet, mentions muster, or wants to coordinate work with other sessions/machines on this repo.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
after-sales
Use when managing post-purchase experience, building customer loyalty, or increasing repeat purchases.
bankr
AI-powered crypto trading agent and LLM gateway via natural language. Use when the user wants to trade crypto, check portfolio balances, view token prices, transfer crypto, manage NFTs, use leverage, bet on Polymarket, deploy tokens, set up automated trading, sign and submit raw transactions, or access LLM models…
bankr-signals
Transaction-verified trading signals on Base blockchain. Agents publish trades.