Claude Octopus is an orchestration project that sends research, design, and coding tasks to Claude Code and other AI model providers so their results can be compared. Developers use it for multi-model work, disagreement detection, reviews, persistent context, and an optional workflow that moves from discovery through delivery. The catalogue entries are its commands, skills, agents, instructions, hooks, plugins, and settings.
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 nyldn/claude-octopus --skill skill-work-slicinggit clone --depth 1 https://github.com/nyldn/claude-octopusWrote 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/nyldn/claude-octopus/skill-work-slicing)<a href="https://agentmods.dev/skills/nyldn/claude-octopus/skill-work-slicing"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-work-slicing/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/nyldn/claude-octopus/skill-work-slicing"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-work-slicing.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 | $0.00033 | $0.01291 |
| Opus 5 | $0.00016 | $0.00646 |
| Sonnet 5 | $0.00007 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
skill-work-slicing 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Slicing
Turn a plan, spec, or the conversation so far into a set of tickets. Each one is a vertical slice — a narrow but complete path through every layer — and each declares the tickets that block it.
This is the step between "we know what we are building" and "someone can pick up
a piece of it". It does not decide anything: if decisions are still open, run
skill-pressure-test first.
Before slicing, map unresolved decision records and their dependencies. Each record names its question, required evidence, owner, resolution, and unblocked implementation. A dependency cycle withholds ready status until it is recut. Invalidated decisions reopen affected work rather than leaving stale completion.
Adapted from to-tickets in
mattpocock/skills (MIT), retargeted at
this repo's trackers.
When To Use
- A plan or spec exists and needs cutting into fileable work.
- A tracking epic is too big to claim and needs children.
- Several people or sessions will work in parallel and need boundaries.
When Not To Use
- Decisions are still open. Slicing unresolved work produces tickets that get
reopened. Use
skill-pressure-test. - The work fits one session. File one ticket, or none.
- You want parallel execution across agents right now, with worktrees and
waves. That is
/octo:parallel, which decomposes into work packages it then runs. This produces tracker state for humans and future sessions.
Inputs
The plan, spec, or conversation. Optionally a parent epic id to hang the slices under.
Workflow
1. Slice vertically
Each slice cuts a narrow but complete path through every layer it touches — schema, API, UI, tests. It is not a horizontal slice of one layer.
- A completed slice is demoable or verifiable on its own.
- Each is sized to fit one fresh context window.
- "Add the database columns" is horizontal and untestable alone. "Store and display the user's timezone, end to end" is vertical.
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.
- 2d ago Changed · +10 lines 056b0deb3890
- 6d ago First seen · 125 lines · 33 tokens per session scan A 073689239d66
skill-work-slicing is a skill published in the GitHub repository nyldn/claude-octopus (4,058 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,291 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 2026-09-03.
Other skills, from other repositories
linear-fetch
This skill should be used when a user input contains a Linear issue reference (e.g., SOL-39 or linear.app/.../issue/ ) and the downstream agent needs the screenshots embedded in the issue as visual context.
drain-labeled-backlog
This skill should be used when draining a labeled issue backlog (deferred-scope-out, code-review, type/security) in one cleanup PR. Groups by code area and delegates to /soleur:one-shot.
cpo
Orchestrates the product domain -- assesses product strategy, validates business models, and delegates to specialist agents (spec-flow-analyzer, ux-design-lead, business-validator, competitive-intelligence). Use individual product agents for focused tasks; use this agent for cross-cutting product strategy and…
file-todos
This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with code review.
campaign-calendar
This skill should be used when generating or refreshing the rolling campaign calendar. Scans knowledge-base/marketing/distribution-content/ markdown frontmatter, groups by status (overdue/upcoming/draft/published), writes a calendar view.
coo
Orchestrates the operations domain -- assesses operational posture, recommends actions, and delegates to specialist agents (ops-advisor, ops-research, ops-provisioner). Use individual operations agents for focused tasks; use this agent for cross-cutting operations strategy and multi-agent coordination. Use cfo for…