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 agentmods add commands/nyldn/claude-octopus/resumegit 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/resume)<a href="https://agentmods.dev/commands/nyldn/claude-octopus/resume"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/resume.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 | $0.00018 | $0.00744 |
| Opus 5 | $0.00009 | $0.00372 |
| Sonnet 5 | $0.00004 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade B, and why
resume scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
helper="$(find "${HOME}/.claude/plugins/cache" "${HOME}/Library/Application Support/Claude" "${LOCALAPPDATA:-/dev/null}/Claude" "${XDG_DATA_HOME:-${HOME}/.local/share}/Claude" -maxdepth 8 -path "*/nyldn-plugins/octo/*/sc This is a copy
91% identical to octo-resume — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/octo:resume — Agent Resume
Your first output line MUST be: 🐙 Octopus Agent Resume
Resume a previously-running Claude agent by ID. Picks up the agent's transcript and continues where it left off.
MANDATORY COMPLIANCE — DO NOT SKIP
When the user explicitly invokes /octo:resume, you MUST call the agent-resume orchestrator path below. You are PROHIBITED from pretending to resume an agent from memory or starting unrelated fresh work without telling the user.
Step 1: Get the Agent ID
If you don't have the agent ID:
- Check
/octo:sentineloutput for running agent IDs - Look in
~/.claude-octopus/results/for recent result files (filename prefix contains agent type + task ID) - The agent ID was shown when the agent was originally spawned
Step 2: Resume
Use the Bash tool to execute:
Preflight check — Ensure plugin root is resolvable (run via Bash tool FIRST):
set -euo pipefail
OCTO_ROOT="${HOME}/.claude-octopus/plugin"
if [[ ! -x "$OCTO_ROOT/scripts/orchestrate.sh" ]]; then
helper="$OCTO_ROOT/scripts/helpers/ensure-plugin-root.sh"
if [[ ! -x "$helper" ]]; then
helper="$(find "${HOME}/.claude/plugins/cache" "${HOME}/Library/Application Support/Claude" "${LOCALAPPDATA:-/dev/null}/Claude" "${XDG_DATA_HOME:-${HOME}/.local/share}/Claude" -maxdepth 8 -path "*/nyldn-plugins/octo/*/scripts/helpers/ensure-plugin-root.sh" -print -quit 2>/dev/null)"
fi
[[ -x "$helper" ]] && bash "$helper" >/dev/null 2>&1 || true
fi
test -x "$OCTO_ROOT/scripts/orchestrate.sh" && echo "plugin-root:ok" || echo "plugin-root:missing"
If the output is plugin-root:missing, stop and ask the user to run /octo:setup.
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh agent-resume "$ARGUMENTS"
Pass the agent ID as $ARGUMENTS. Optionally append a follow-up prompt:
# Just agent ID (resumes with "Continue where you left off.")
orchestrate.sh agent-resume abc123
# Agent ID + custom prompt
orchestrate.sh agent-resume abc123 "fix the failing test in auth.ts"
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.
- yesterday First seen · 73 lines · 18 tokens per session scan B 7eaa55629940
resume is a command published in the GitHub repository nyldn/claude-octopus (4,050 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 744 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 91% identical to octo-resume, differing in 3 lines, and is treated as a copy.
Other commands, from other repositories
setup-agents
Scaffold a multi-agent AI setup for any repo. Scans the codebase, interviews the developer, generates agent configs for whichever AI tools the repo uses (Copilot, Claude Code, Cursor, Codex, Windsurf). Use when asked to "set up agents", "scaffold Copilot agents", or "create an AGENTS.md".
datadog
Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live incident investigation using the Datadog MCP server. Covers Terraform-managed Datadog resources.
aws-profile
AWS profile management for MCP servers — discover profiles across SSO, Granted, and assumed-role chains, check credential TTL, switch profiles across VS Code and Claude Code MCP configs, and scan AWS Organization accounts.
agent-triage
Find and triage Quickchat conversations that need a human.
add-email-railway
Integrate email functionality using Nodemailer or Resend API. Set up SMTP configuration with environment variables. Create email templates using React Email for type-safe component-based emails. Implement send email API endpoint in Express. Add email validation and rate limiting. Handle delivery failures with retry…
tag
Switch the active time-keeper label (like start, but semantically a switch).