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 create-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/create-plugin)<a href="https://agentmods.dev/skills/shreypaharia/octomux/create-plugin"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/create-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/create-plugin"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/create-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, 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 Prompt Injection · line 59 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 61 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 62 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 65 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 66 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 67 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 71 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Rogue Agent · line 240 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00043 | $0.04309 |
| Opus 5 | $0.00022 | $0.02155 |
| Sonnet 5 | $0.00009 | $0.00862 |
| Haiku 4.5 | $0.00004 | $0.00431 |
Grade A, and why
create-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 9d 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an octomux plugin
Author a plugin package that registers into octomux at boot: a workflow kind, an
integration provider, or a harness. A plugin is a normal npm package that exports
an apply(ctx) function; octomux loads it in-process via import() — see the
add-plugin skill for the trust implications of that before you ship one.
Package layout
octomux-plugin-<name>/
package.json # name, version, type: module, main (or exports)
index.js # the apply(ctx) export
kinds/ # optional — schedule-kind presets this plugin ships
<kind>.json
package.json needs a real main/exports field once published — during local
dev (see "Testing it locally" below) a bare index.js with no package.json also
resolves, because Node's module resolution falls back to index.js when no
package.json is present. Don't rely on that for anything you publish.
The apply(ctx) export
export function apply(ctx) {
ctx.logger.info({}, 'plugin applied');
ctx.workflows.register({ kind: 'changelog', displayName: 'Changelog', surfaces: ['feed'] });
}
apply can also hang off a default export (export default { apply }) — both
forms are read as "this module is the plugin."
apply(ctx) runs once at boot, in manifest order, each in its own try/catch — one
plugin throwing never takes down another. It has a 10-second budget
(DEFAULT_APPLY_TIMEOUT_MS in server/plugins/loader.ts); overrun it and the
loader marks the plugin failed (phase apply) and revokes its context — any
registrar call your apply() makes after that point throws context revoked — … refused because apply() overran its timeout budget instead of quietly landing
in the live registry after the loader already reported you failed. Keep apply()
synchronous-fast; don't do network calls or slow I/O in it.
An optional reconcile?(ctx) export exists on the OctomuxPlugin interface for
plugins owning out-of-process state (worktrees, tmux, files written into a repo)
and is documented as required for that case — but nothing in the codebase
calls it yet (server/plugins/loader.ts explicitly does not; boot has no other
caller). Export it if your plugin owns that kind of state so you're ready when the
wiring lands, but don't depend on it running today. apply() is currently the
only place your plugin's own code executes at boot.
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.
- 9d ago First seen · 340 lines · 43 tokens per session scan A bec6244d2da3
create-plugin is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 8d ago), licensed MIT. It adds 43 tokens to every session and 4,309 once invoked, about $0.0002 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
qa
Run scalable, isolated live QA for nac development. The top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this skill using all test…
chrome-automation
A browser-automation toolkit for controlling Chrome to visit pages, interact with forms, collect data, run tests, and create screenshots or PDFs.
agent-tester
Test agent: dry-run, unit, integration, compatibility.
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
agentplane-testkit-migration
Use when migrating Agentplane tests to @agentplane/testkit, replacing local test helpers, fixing testkit export/build failures, splitting large CLI/backend suites, or diagnosing missing testkit dist exports in package builds.
verifying-final-artifacts
Verifies the delivered artifact a consumer actually receives (a figure, chart, PDF, SVG, screenshot, compiled build, or deployed response) by regenerating it fresh and directly observing the output, not the source that produces it, and ends in one honest verdict. Use when the deliverable is a produced artifact and…