octopus

octopus is a skill for Claude Code, Codex from davekindl/skills. It costs 87 tokens per session (992 once invoked), scanned A, original, MIT.

A configurable overnight system that runs separate tasks in parallel, moves them through ordered phases, and produces one report.

In plain words
What is it for?
Use it for nightly batches of independent tasks such as checking project state, building or drafting changes, gathering research, running benchmarks, and assembling a morning summary.
Why use it?
It lets recurring project work continue without constant supervision while keeping the results in a written record for review later.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it for nightly batches of independent tasks such as checking project state, building or drafting changes, gathering research, running benchmarks, and assembling a morning summary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davekindl/skills/octopus
Install

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.

Any agent
npx skills add davekindl/skills --skill octopus
Clone the repo
git clone --depth 1 https://github.com/davekindl/skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for octopus

README.md
[![agentmods](https://agentmods.dev/badge/skills/davekindl/skills/octopus/github.svg)](https://agentmods.dev/skills/davekindl/skills/octopus)
Your own site
<a href="https://agentmods.dev/skills/davekindl/skills/octopus"><img src="https://agentmods.dev/badge/skills/davekindl/skills/octopus/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.

agentmods 80×15 button for octopus

Your own site · 80×15
<a href="https://agentmods.dev/skills/davekindl/skills/octopus"><img src="https://agentmods.dev/badge/skills/davekindl/skills/octopus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.00992
Opus 5 $0.00044 $0.00496
Sonnet 5 $0.00017 $0.00198
Haiku 4.5 $0.00009 $0.00099

Measured 12d ago against content hash c03ae16f82f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

octopus 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 12d 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.

skills/octopus/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Octopus — Autonomous Nightly Operations

Point it at your projects, define the arms, let it run overnight. Read the report over coffee.

Octopus is a pattern for unattended parallel operations: a small orchestrator that fans a batch of independent tasks ("arms") out across a few ordered phases, runs them concurrently, collects the results, and prints a single morning briefing. It turns "things I keep meaning to do" into "things that happen every night."

This is a template you configure, not a fixed program. The value is the architecture — phases, parallel arms, a durable ledger, and a report — which you fill with the arms that matter for your projects.

The architecture

PHASE 1 — SENSE      (read state, gather signals)      arms run in parallel
PHASE 2 — ACT        (evolve, build, draft, audit)     arms run in parallel
PHASE 3 — GROW       (data, benchmarks, research)      arms run in parallel
PHASE 4 — REPORT     (reconcile ledgers, build report) single arm

Each arm is a self-contained task with a clear goal, its own inputs, and a written result. Arms in the same phase have no dependencies on each other, so they run concurrently (via parallel agent dispatch). Later phases can read what earlier phases wrote.

Configuring your arms (examples — pick what fits your projects)

Arm type What it does overnight
Product evolution Run an improvement pass on one project; write a change proposal for you to review
Security/quality audit Scan a codebase or product for defects, write a prioritized findings list
Data growth Pull fresh signals (market, competitor, keyword) into a local knowledge store
Content drafting Draft the next posts/emails from your existing material for morning review
Outreach prep Assemble a shortlist + first-draft messages for you to send by hand
Benchmarking Re-run your metrics/tests and flag regressions vs the last accepted run
Housekeeping Reconcile your notes/queues so nothing rots (a task ledger, a backlog file)
Reporting Compose the visual morning briefing from every arm's result

Read the full file on GitHub · 83 lines

Changes

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.

  1. 12d ago First seen · 83 lines · 87 tokens per session scan A c03ae16f82f7

Subscribe to this mod's changes

octopus is a skill published in the GitHub repository davekindl/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 992 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens