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-rollbackgit 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-rollback)<a href="https://agentmods.dev/skills/nyldn/claude-octopus/skill-rollback"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-rollback.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 YARA Match · line 228 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Anti-Refusal · line 229 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Tool Misuse · line 231 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 228 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.01802 |
| Opus 5 | $0.00012 | $0.00901 |
| Sonnet 5 | $0.00005 | $0.00360 |
| Haiku 4.5 | $0.00002 | $0.00180 |
Grade A, and why
skill-rollback 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 8d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint Rollback
Safely rollback to a previous checkpoint while preserving lessons learned.
Core principle: List checkpoints → Confirm explicitly → Create safety backup → Restore → Preserve lessons.
Subcommand Detection
Parse the user's request to determine mode:
| User Request | Mode | Action |
|---|---|---|
list, show checkpoints, no argument |
LIST | Show available checkpoints |
octo-checkpoint-* tag name |
ROLLBACK | Rollback to specific checkpoint |
Mode: LIST (Default)
Step 1: Fetch Available Checkpoints
# List all octo checkpoints with dates
git tag -l "octo-checkpoint-*" --sort=-creatordate --format='%(refname:short)|%(creatordate:short)|%(contents:subject)'
Step 2: Present Checkpoint Table
## Available Checkpoints
| Tag | Created | Description |
|-----|---------|-------------|
| octo-checkpoint-post-discover-20260203-143022 | 2026-02-03 | After Discover phase |
| octo-checkpoint-post-define-20260203-150145 | 2026-02-03 | After Define phase |
Usage: `/octo:rollback <tag-name>`
If no checkpoints found:
No checkpoints found. Checkpoints are created automatically after each Octopus phase.
To create a manual checkpoint:
git tag -a octo-checkpoint-manual-$(date +%Y%m%d-%H%M%S) -m "Manual checkpoint"
Mode: ROLLBACK
Step 1: Validate Checkpoint Exists
# Check if tag exists
git tag -l "$CHECKPOINT_TAG" | grep -q . || echo "TAG_NOT_FOUND"
If tag not found:
Checkpoint '$CHECKPOINT_TAG' not found.
Available checkpoints:
[show list output]
STOP. Do not proceed.
Step 2: Show What Will Be Affected
# Get list of files that will be changed
git diff --name-status HEAD $CHECKPOINT_TAG
Present clearly:
## Rollback Preview
**Rolling back to:** `octo-checkpoint-post-discover-20260203-143022`
**Created:** 2026-02-03 14:30:22
**Description:** After Discover phase
### Files That Will Be Changed
| Status | File |
|--------|------|
| M | src/auth/login.ts |
| D | src/auth/oauth.ts |
| A | src/legacy/old-auth.ts |
Legend: M=Modified, D=Deleted, A=Added (relative to current state)
### Protected Files (Will NOT be changed)
- `.octo/LESSONS.md` - Lessons are always preserved
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.
- 8d ago First seen · 275 lines · 24 tokens per session scan A 9da76e229763
skill-rollback is a skill published in the GitHub repository nyldn/claude-octopus (4,054 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,802 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 2026-08-30.
Other skills, from other repositories
changelog
This skill should be used when creating changelogs for recent merges. Analyzes PR labels, issues, and descriptions to generate formatted summaries.
release
Release a new version of the DevoxxGenie IntelliJ plugin — prompt for the target version, bump it in the build files, write a curated CHANGELOG.md entry and plugin.xml change-notes from the git/PR history since the last tag, build to verify, then commit, tag, and publish a matching GitHub release. Use this whenever…
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).