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
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add nyldn/claude-octopus/plugin install octoWrote 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-usage)<a href="https://agentmods.dev/commands/nyldn/claude-octopus/octo-usage"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/octo-usage/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/commands/nyldn/claude-octopus/octo-usage"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/octo-usage.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.00518 |
| Opus 5 | $0.00013 | $0.00259 |
| Sonnet 5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
octo-usage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- usage — 91% identical, 3 lines differ
What it actually says
Usage Report (/octo:usage)
Your first output line MUST be: 🐙 Octopus Usage Report
Produce a per-provider, per-skill, and per-MCP-server cost and token breakdown from recorded Octopus usage artifacts. Output schema matches Claude Code's native /usage report (claude-code/usage-v1), so results can be compared or merged with the host session's own usage pane.
EXECUTION CONTRACT (Mandatory)
STEP 1: Run the report helper
OCTO_ROOT="${CLAUDE_PLUGIN_ROOT:-${HOME}/.claude-octopus/plugin}"
"$OCTO_ROOT/scripts/helpers/usage-report.sh" --view usage --format table
If the user asked for machine-readable output (or passed --format json):
OCTO_ROOT="${CLAUDE_PLUGIN_ROOT:-${HOME}/.claude-octopus/plugin}"
"$OCTO_ROOT/scripts/helpers/usage-report.sh" --view usage --format json
The helper reads:
~/.claude-octopus/usage/*.jsonl— JSONL records written byhooks/subagent-stop-gate.shand provider adapters~/.claude-octopus/results/**/summary.json— council and workflow roster artifacts (query counts)
STEP 2: Present the breakdown
Show the helper's table output directly. Then add a one-paragraph interpretation:
- Which provider drove the most estimated cost
- Whether any external CLI seat (🔴 Codex, 🧭 Antigravity) dominates and could be swapped for an included provider
- Whether MCP server usage is material
STEP 3: Flag empty data honestly
If the helper prints No usage records found, say so and point the user at OCTOPUS_SUBAGENT_GATE_STRICT and the SubagentStop gate hook (hooks/subagent-stop-gate.sh), which populates the usage log as subagents complete. Do not fabricate numbers.
Cost reference
Rates come from config/model-pricing.tsv. The helper is the only calculator.
Providers with subscription or local backends such as agy, Copilot, Ollama,
Cursor Agent, and native OpenCode report $0.00.
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.
- 6d ago First seen · 49 lines · 26 tokens per session scan A 393cc5efb127
octo-usage is a command published in the GitHub repository nyldn/claude-octopus (4,056 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 518 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
portfolio-assess
Assess AI literacy across multiple repositories — aggregate assessments into a portfolio view with level distribution, shared gaps, and prioritised improvements.
zestimate
Get the Zestimate (home value) and rent Zestimate for a property.
ma-strategy
Develop M&A strategy including target screening, synergy analysis, or integration planning.
mmm-reconcile
Reconcile modelled media spend against the finance ledger, classify the shape of any disagreement, and produce the variance report needed before results are presented.
clob-trades
Access trade execution data, historical trades, and user trade activity.
financial-model
Generate a 6-year ecommerce financial model without writing the narrative business plan.