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 skill-security-auditgit 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/skill-security-audit)<a href="https://agentmods.dev/skills/nyldn/claude-octopus/skill-security-audit"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-security-audit/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/skill-security-audit"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Privilege Escalation · line 78 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Agent Snooping · line 115 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Data Exfiltration · line 109 Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.Fix: Remove unnecessary filesystem scanning. If file access is needed, use explicit, scoped paths. Avoid reading ~/.ssh, ~/.aws, or credential directories.
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 | $0.00024 | $0.02150 |
| Opus 5 | $0.00012 | $0.01075 |
| Sonnet 5 | $0.00005 | $0.00430 |
| Haiku 4.5 | $0.00002 | $0.00215 |
Grade A, and why
octopus-security-audit scanned grade A 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 2d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/plugins/*/plugin.json 2>/dev/null | grep -E '"source"|"registry"' Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit Skill
Your first output line MUST be: 🐙 **CLAUDE OCTOPUS ACTIVATED** - Security Audit
Invokes the security-auditor persona for thorough security analysis during the ink (deliver) phase. Supports both quick OWASP scanning and full adversarial red/blue team testing.
Usage
# Quick scan via security-auditor persona
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh spawn security-auditor "Scan for SQL injection vulnerabilities"
# Adversarial red team via squeeze workflow
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh squeeze "Security audit the authentication module"
# Via auto-routing (detects security intent)
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "security audit the payment processing module"
Modes (Auto-Detected)
| Mode | Auto-Trigger | Confidence Gate | Scope |
|---|---|---|---|
| Quick (default) | Standard security scan, no sensitive files in diff | 8/10 — only high-confidence findings | Changed files only |
| Deep (auto-escalated) | Diff touches auth/security/CI files, OR explicit request | 2/10 — flag anything suspicious | Entire codebase |
Auto-escalation to Deep mode: The skill automatically switches to Deep mode when ANY of these are true:
- Diff includes files matching:
*auth*,*login*,*password*,*session*,*token*,*secret*,*crypt*,*oauth*,*saml*,*jwt*,*permission*,*rbac*,*acl* - Diff includes CI/CD files:
.github/workflows/*,Dockerfile*,docker-compose*,.gitlab-ci* - Diff includes dependency files:
package-lock.json,yarn.lock,Gemfile.lock,requirements.txt,go.sum - The user explicitly says "deep", "full", "comprehensive", or "CSO"
No user action needed — mode detection happens automatically from the git diff context.
Model Selection Caveat: Fable 5.1
By default, do not dispatch security-audit passes to Claude Fable 5.1 or the preserved Fable 5 ID. Their safety classifiers can refuse adversarial red-team phrasing in authorized audits. Route these passes to OCTOPUS_FABLE5_FALLBACK_MODEL (default claude-opus-5) and keep prompts defensively framed (find and report vulnerabilities; do not request working exploits). Reject an exact model-qualified override that targets claude-fable-5-1 or claude-fable-5. On refusal, retry exactly once on the fallback unless OCTOPUS_FABLE5_NO_RETRY=1; when retries are disabled or the retry refuses, surface the refusal without further dispatches. OCTOPUS_FABLE5_MODE=off is the explicit exception: it disables automatic rerouting for ordinary environment pins, while exact Fable security seats still fail closed. Details: skills/blocks/fable5-prompting.md.
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.
- 2d ago Changed d04c4c779e50
- 9d ago First seen · 208 lines · 24 tokens per session scan A 21a82bdbe8ca
octopus-security-audit is a skill published in the GitHub repository nyldn/claude-octopus (4,056 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,150 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). 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.
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.
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.
gemini-imagegen
This skill should be used when generating or editing images via the Gemini API: text-to-image, edits, multi-turn refinement, style transfer, mockups.
legal-audit
This skill should be used when auditing existing legal documents for compliance gaps, outdated clauses, missing disclosures, and cross-document consistency. It scans a project for legal documents and displays findings inline.