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-pressure-testgit 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-pressure-test)<a href="https://agentmods.dev/skills/nyldn/claude-octopus/skill-pressure-test"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-pressure-test/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-pressure-test"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-pressure-test.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 | $0.01153 |
| Opus 5 | $0.00016 | $0.00576 |
| Sonnet 5 | $0.00007 | $0.00231 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
skill-pressure-test 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pressure Test
Interview the user relentlessly about a plan, decision, or design until you both reach a shared understanding of it. Walk each branch of the decision tree, resolving dependencies between decisions one at a time.
This is not brainstorming. skill-thought-partner opens a space up and looks for
what might be there; this closes one down and looks for what is wrong with it.
Use this when there is already a position on the table and the risk is that it is
wrong in a way nobody has said out loud.
Adapted from the grilling skill in
mattpocock/skills (MIT).
When To Use
- The user has a plan, spec, or design and wants it attacked before they commit.
- A decision keeps getting deferred because its dependencies are tangled.
- Scope feels slippery and nobody can say precisely what is in it.
- Before a large or hard-to-reverse change, where being wrong is expensive.
When Not To Use
- To generate options. That is
skill-decision-support. - To explore an open space with no position yet. That is
skill-thought-partner. - When the user wants the work done, not examined. Say so and stop.
- When you can settle the question by reading the codebase. Read it instead.
Inputs
The plan, decision, or design under test, in whatever form exists — a document, a paragraph, or just the last few turns of conversation. Nothing needs writing up first; extracting the shape is part of the job.
Workflow
Ask one question at a time. Wait for the answer before asking the next. A batch of questions is a questionnaire, and it gets questionnaire answers: shallow, and shaped by whichever one the reader happened to care about. One question, answered properly, changes what the next question should be.
Carry a recommended answer with every question. "What should happen when the token expires?" is work handed back. "What should happen when the token expires? I would refresh silently and only surface an error if the refresh fails, because the alternative interrupts the user mid-task — do you agree?" is a question that can be answered in one word, and disagreed with precisely.
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 · +8 lines 2e10f5e4eee8
- 10d ago First seen · 103 lines · 33 tokens per session scan A b31a76209c1f
skill-pressure-test 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 1,153 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
ai-context
Generates, updates, and audits AGENTS-first AI IDE context files. Builds canonical AGENTS.md plus thin bridges for Claude Code, Cursor (modern .cursor/rules/.mdc), Copilot, Cline (.clinerules/ directory), Windsurf, Gemini CLI, Codex CLI, and OpenCode. Use for creating, regenerating, fixing, or promoting context files…
architecture
This skill should be used when managing Architecture Decision Records or C4 diagrams.
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.
invoice
This skill should be used when the founder wants to get paid through their own Stripe account: list who owes them, create and send an invoice behind a human-approval preview, or chase an overdue one. Test-mode only in v1.
legal-generate
This skill should be used when generating draft legal documents for a project or company. It gathers company context interactively, invokes the legal-document-generator agent, and writes markdown output.
agent-native-audit
This skill should be used when conducting a scored agent-native architecture review. It launches 8 parallel sub-agents to audit action parity, context injection, CRUD completeness, capability discovery, and prompt-native features.