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.
git 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/commands/nyldn/claude-octopus/octo-loop)<a href="https://agentmods.dev/commands/nyldn/claude-octopus/octo-loop"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/octo-loop.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00016 | $0.01042 |
| Opus 5 | $0.00008 | $0.00521 |
| Sonnet 5 | $0.00003 | $0.00208 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
octo-loop scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ measured 4d 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 โ 137 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
Loop - Iterative Execution Skill
Your first output line MUST be: ๐ Octopus Loop Mode
Instructions
Read and follow the full skill instructions from:
${HOME}/.claude-octopus/plugin/.claude/skills/skill-iterative-loop/SKILL.md
Quick Usage
Just use natural language:
"Loop 5 times auditing, enhancing, testing"
"Keep trying until all tests pass"
"Iterate until performance improves"
Or use the explicit command:
/octo:loop "run tests and fix issues" --max 5
/octo:loop "optimize performance until < 100ms"
Loop Execution Approach
- Define Goal: Clear success criteria and exit conditions
- Set Max Iterations: Safety limit to prevent infinite loops
- Execute: Run the task/operation
- Evaluate: Check if goal is met or progress made
- Loop or Complete: Continue if needed, stop when done
What You Get
- Systematic iteration with progress tracking
- Clear exit conditions (max iterations or goal met)
- Progress metrics after each iteration
- Stall detection (stops if no progress)
- Final summary of all iterations
Use Cases
Testing Loops:
"Loop until all unit tests pass, max 3 attempts"
"Keep fixing failing tests until test suite is green"
Optimization Iterations:
"Loop 5 times optimizing query performance"
"Iterate until API response time is under 100ms"
Progressive Enhancement:
"Loop around 3 times enhancing error handling"
"Iterate improving code quality until score > 80"
Retry Patterns:
"Try up to 5 times to connect to the database"
"Loop until deployment succeeds, max 3 retries"
Safety Features
- Max iterations enforced: Never infinite loops
- Stall detection: Stops if no progress after N iterations
- Clear exit criteria: Always know when to stop
- Progress tracking: See improvement each iteration
Parameters
- Task/Goal: What to execute or achieve
- Max iterations: Safety limit (default: 5, max: 20)
- Exit condition: When to stop ("until tests pass", "until score > X")
- Progress metric: How to measure improvement
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.
- 4d ago First seen ยท 137 lines ยท 16 tokens per session scan A 019b3b942d7c
octo-loop is a command published in the GitHub repository nyldn/claude-octopus (4,054 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 1,042 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 2026-09-03.
Other commands, from other repositories
implement-fix
Minimal pipeline for test-fixing tasks.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
verify
You are invoking the verify skill - comprehensive verification following Boris Cherny's pattern.
improve-test-quality
Analyze and improve existing test quality with better assertions, coverage, and maintainability.
fix-test
Auto-diagnose and fix failing tests โ identifies root causes and applies fixes.