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 flow-discovergit 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/flow-discover)<a href="https://agentmods.dev/skills/nyldn/claude-octopus/flow-discover"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/flow-discover/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/flow-discover"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/flow-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 138 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium Rogue Agent · line 592 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00000 | $0.07658 |
| Opus 5 | $0.00000 | $0.03829 |
| Sonnet 5 | $0.00000 | $0.01532 |
| Haiku 4.5 | $0.00000 | $0.00766 |
Grade A, and why
flow-discover 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 9d 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 — 896 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{PREAMBLE}}
Compaction-Resistant Contract
- Dispatch MUST go through background agents that call
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh probe-single; direct single-model research is not a valid substitute. - Use the dynamic fleet from
build-fleet.sh; the plugin can route across Codex, Antigravity, Copilot, Qwen, OpenCode, Ollama, Perplexity, OpenRouter, Cursor Agent, and Claude depending on local availability. - Before synthesis, run
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh agent-summaryand use only providers reported asok,degraded, ortimeoutwith usable output. - For
standardanddeepresearch, require at least 2 usable provider outputs unless fewer providers are installed; failed/rejected providers are reported as gaps, not cited as evidence.
Pre-Discovery: Optional Project Persistence
Workflow state is stored in the host workspace by default. Only create the
project-local .octo/ lifecycle artifacts when the user explicitly opts in by
setting OCTOPUS_PROJECT_PERSISTENCE=true.
if [[ "${OCTOPUS_PROJECT_PERSISTENCE:-false}" == "true" ]]; then
if [[ ! -d ".octo" ]]; then
echo "📁 Initializing opt-in .octo/ project state..."
if ! "${HOME}/.claude-octopus/plugin/scripts/octo-state.sh" init_project; then
echo "Discover incomplete: could not initialize opt-in project state." >&2
exit 1
fi
fi
if ! "${HOME}/.claude-octopus/plugin/scripts/octo-state.sh" update_state \
--phase 1 \
--position "Discovery" \
--status "in_progress"; then
echo "Discover incomplete: could not persist in-progress state." >&2
exit 1
fi
fi
Native Plan Mode Compatibility (v7.23.0+)
IMPORTANT: claude-octopus workflows are designed to persist across context clearing.
Detecting Native Plan Mode
Check if native plan mode is active:
# Check for native plan mode markers
if [[ -n "${PLAN_MODE_ACTIVE}" ]] || claude-code plan status 2>/dev/null | grep -q "active"; then
echo "⚠️ Native plan mode detected"
echo ""
echo " Resolve Claude Octopus workflow state with: octopus state-path"
echo " State will persist across plan mode context clears"
echo " Multi-AI orchestration will continue normally"
echo ""
fi
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 896 lines · 0 tokens per session scan A 45d01930e297
flow-discover is a skill published in the GitHub repository nyldn/claude-octopus (4,056 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,658 tokens. 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.