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-taskgit 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-task)<a href="https://agentmods.dev/skills/shreypaharia/octomux/create-task"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/create-task/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-task"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/create-task.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 Rogue Agent · line 6 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 | $0.00028 | $0.02566 |
| Opus 5 | $0.00014 | $0.01283 |
| Sonnet 5 | $0.00006 | $0.00513 |
| Haiku 4.5 | $0.00003 | $0.00257 |
Grade A, and why
create-task 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an octomux task
Dispatch an autonomous Claude Code agent to work on a feature, bugfix, or code change via octomux.
Delegate the exploration — do NOT do it yourself. Do not read the repo's code, README, or git diffs to figure out how the work should be done — that is the worker's job. The worker explores the real code and owns the implementation. Your task description is a goal-oriented brief: the WHAT and WHY plus verifiable acceptance criteria, hard constraints, non-goals, and orientation pointers — never a step-by-step procedure ("edit file X, then Y"). Gather only the minimum needed to dispatch: the repo path, base branch, and (if given) ticket details. A step plan you write without reading the code is stale and constrains a capable worker. (See the goal-oriented brief shape in Step 5.)
Steps
-
Understand the goal:
- Ask the user what they want built/fixed, or infer from context (e.g. a Linear/Jira ticket URL, a bug description, a feature request)
- If given a ticket URL or key (e.g.
BAC-843,PROJ-843), fetch the ticket details. Ticket keys match[A-Z][A-Z0-9]+-\d+. Decide tracker (Linear vs Jira) using the rules below.
How to decide which tracker the key belongs to:
- Full URL with
linear.app/→ Linear. - Full URL with
*.atlassian.net/→ Jira. - Bare key (e.g.
BAC-123):- Call
mcp__plugin_linear_linear__list_teams()and check whether the key prefix matches a Linear team's key → Linear. - Otherwise treat as Jira.
- Call
- If ambiguous (both could match), prefer
defaultTrackerfrom~/.octomux/settings.json. - The configured trackers and their defaults are the source of truth — run
octomux list-integrations --jsonto see enabled Jira/Linear integrations with theirbase_url,default_project, anddefault_team_key(secrets are masked).
Fetching Linear issue details:
- Extract the issue key (e.g.
BAC-843). - Use Linear MCP tools:
mcp__plugin_linear_linear__get_issue({ query: '<issue-key>' })to fetch title, description, state, labels, priority, team, project.
- Map fields to the prompt template:
title→ task title + What sectiondescription→ Context section (extract acceptance criteria if present)labels[].name/priority→ urgency hints in Why sectionteam.key+team.id+project.id+id(issue UUID) → ref metadata (Step 6a below)state→ ignored (octomux owns workflow state)
- Branch naming uses the same convention:
feat/BAC-123-add-position-sync.
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 · 223 lines · 28 tokens per session scan A ecc6fe947039
create-task is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 2,566 once invoked, about $0.0001 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…
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.
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.