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-plan)<a href="https://agentmods.dev/commands/nyldn/claude-octopus/octo-plan"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/octo-plan/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-plan"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/octo-plan.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 | $0.00025 | $0.05475 |
| Opus 5 | $0.00013 | $0.02738 |
| Sonnet 5 | $0.00005 | $0.01095 |
| Haiku 4.5 | $0.00003 | $0.00547 |
Grade A, and why
octo-plan 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 5d 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:
- plan — 100% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan - Intelligent Plan Builder
Load skills/blocks/engineering-method-selection.md from the installed plugin
and apply only the methods relevant to this task. Preserve this entry point's
execution contract and output format. Read referenced skills as instructions;
do not invoke the current command recursively or add provider calls from a seat.
Creates strategic execution plans based on user intent. Saves plans for review and optional execution with /octo:embrace.
Key Behavior
- Creates plans - Captures intent, analyzes requirements, generates weighted execution strategy
- Saves to files - Stores each plan and intent contract in a unique run directory under the project-owned
.octo/plans/namespace, or under octo-owned session storage when there is no project - Doesn't execute - Plans are saved for review; execution requires user confirmation
- Optional execution - Can load
/octo:embraceafter explicit user approval or execute later - Prototype handoff - Can propose one bounded experiment without writing or launching providers in native plan mode
Prototype proposal
When one risky assumption blocks the plan, offer a prototype with one question,
hypothesis, deadline, artifact path, source revision, and success signal. In native
read-only plan mode, present the proposal only. After explicit execution approval,
load skill-prototype and store artifacts through scripts/plan-storage.sh.
Choosing a prototype does not authorize deployment, provider calls, browser login,
repository rewrites, or new permissions.
Before filing implementation tasks, map unresolved decisions and their dependency graph. A cycle withholds ready status. Claims must use the configured tracker's atomic operation and be read back before work starts. On tracker failure, save an explicitly unfiled proposal in the plan directory and stop tracker writes.
🤖 INSTRUCTIONS FOR CLAUDE
MANDATORY: Detect Plan Mode Write Conflict Before Starting
THIS CHECK RUNS FIRST — before intent capture, before any artifact write.
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.
- 5d ago Changed · +20 lines 8465db220715
- 9d ago First seen · 634 lines · 25 tokens per session scan A 96557b99d513
octo-plan is a command published in the GitHub repository nyldn/claude-octopus (4,062 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 5,475 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
next
Read the active sprint’s current status. Refresh stale compilation using grainulator compile --dir or grainulator.compile. Use the resulting nextactions with the user’s current scope and authorization. Output only the two Auto and Manual lists below, with no recap, status counters or offer to continue. Continue useful…
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
feat
Kick off tasks creation for a new feature (4-item interview before invoking pm-agent; an epic-sized requirement routes to phased decomposition, a feature already built on one platform routes to cross-platform parity, a change that touches no endpoint routes to client-only).
bb-tasks
A command for displaying a numbered list of unfinished tasks, ordered by their deadlines, with each task’s completion status.
close-sprint
Close the sprint — record Increment + velocity, return unfinished stories/bugs to the backlog.
workspace-status
(Workspace) Dashboard across all managed repos — sprint, unreleased, blocked, last sync.