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 add-plugingit 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/add-plugin)<a href="https://agentmods.dev/skills/shreypaharia/octomux/add-plugin"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/add-plugin/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/add-plugin"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/add-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 186 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00053 | $0.02491 |
| Opus 5 | $0.00026 | $0.01246 |
| Sonnet 5 | $0.00011 | $0.00498 |
| Haiku 4.5 | $0.00005 | $0.00249 |
Grade A, and why
add-plugin 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install and manage an octomux plugin
Plugins are npm packages listed in a manifest file (octomux.yml), loaded
in-process at boot. This skill covers the install/manage lifecycle from the
outside — for authoring a plugin, see create-plugin.
Security posture — read this before installing anything
A plugin runs in-process with full Node privileges. There is no sandbox.
It gets the same DB handle, the same credentials, and the same process.env as
octomux itself. One line in a malicious apply() can flip
OCTOMUX_CAPABILITY_GATE_ENABLED and disable every human-approval gate for every
task launched afterward. Installing a plugin is equivalent to running its code —
treat npm install-level trust decisions (who published it, do you trust the
maintainer, has the tarball hash changed) as seriously as you would for any
dependency with production DB access, because that's what it has.
There is no plan to add an in-process containment boundary. The controls that exist today:
- The manifest row schema (
server/plugins/manifest.ts) hasversionandintegrityfields for exact-pinning, but today only their shape is validated (both must be strings) — the loader does not fetch/verify a tarball hash againstintegritybeforeimport()ing. Treat both as documentation for now, not an enforced guarantee. octomux start --safe-modeas the kill switch (see below).
There is no attribution trail today distinguishing a plugin-driven change from a core one (e.g. a task row a plugin's workflow mutated looks identical in the event log to one core mutated) — don't assume you can audit your way out of a bad install after the fact.
Where packages live
<prefix>/node_modules/<pkg>
<prefix> is OCTOMUX_PLUGIN_PREFIX if set, else octomuxRoot() (~/.octomux
in production, ./data in dev). The manifest itself lives at
OCTOMUX_PLUGIN_MANIFEST if set, else <prefix>/octomux.yml — note these two are
independently overridable, so a plugin prefix and a manifest path don't have to
be siblings unless you leave both at their defaults.
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 · 217 lines · 53 tokens per session scan A 9ea8c9186065
add-plugin is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 9d ago), licensed MIT. It adds 53 tokens to every session and 2,491 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
deslop
Audit or apply evidence-backed, test-first subtractive cleanup for accumulated agent-created test bloat, verification theater, and defensive or fallback bloat while preserving independent external behavior. Invoke explicitly for semantic simplification, not generic refactoring.
learning-from-experience
Turns incidents, near misses, bad handoffs, review surprises, escaped bugs, and signals from real use into lasting fixes to your safeguards. Use after something went wrong or nearly did and a future safeguard should change. Do not use during a live incident, which comes first, or to blame someone.
reporting-shared-defects
Routes a defect found in a shared or supplied artifact (a shared prompt, skill, dependency, model, eval, or template) to the downstream teams, agents, and releases that depend on it, not just a local fix. Use when a discovered defect affects others who consume the same artifact. Do not use for a defect local to your…
responding-to-incidents
Runs a live incident the stabilize-first way — name a commander, separate facts from hypotheses, prefer reversible actions, communicate on a cadence, and drive corrective actions to closure. Use when production is broken, data is at risk, or an agent action caused harm. Do not use for routine non-incident work, or as…
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.