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-verification-gategit 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-verification-gate)<a href="https://agentmods.dev/skills/nyldn/claude-octopus/skill-verification-gate"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-verification-gate/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-verification-gate"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-verification-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 88 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 | $0.00020 | $0.01352 |
| Opus 5.5 | $0.00008 | $0.00541 |
| Sonnet 5.5 | $0.00004 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
skill-verification-gate 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 25d 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:
- skill-verify — 86% identical, 21 lines differ
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Gate
Portable feature evidence
Load the selected feature's policy provenance and open-marker count through the existing boundary adapter. Cite the exact policy passage and conflicting plan action for any verified policy violation. Report unresolved decisions and which tasks depend on them. Stable task completion needs parent verification tied to the current task-contract digest; a checkbox, model claim or historical manifest alone cannot prove completion. Retain result-to-task mappings through correction, cancellation and resume.
The Iron Law
If you haven't run the verification command in this turn, you cannot claim it passes.
The Gate
Before claiming any success or expressing satisfaction:
- IDENTIFY — What command proves this claim?
- RUN — Execute the full command (fresh, not cached)
- READ — Full output, check exit code, count failures
- VERIFY — Does output actually confirm the claim?
- ONLY THEN — State the claim WITH evidence
Skip any step = the claim is unverified.
Rationalization Table
| Excuse | Reality |
|---|---|
| "I ran the tests earlier this session" | Earlier is not fresh. Code changed since. Run again. |
| "The edit was trivial, it can't break anything" | Trivial edits break builds daily. The gate has no size exemption. |
| "The subagent reported success" | Agent reports are claims, not evidence. Verify independently. |
| "CI will catch it anyway" | CI is the safety net, not the verification. Verify before push. |
| "I'm confident this works" | Confidence is not evidence. Run the command. |
| "Running the full suite is slow" | Then run the targeted suite — but run something, fresh. |
What Counts as Evidence
| Claim | Requires | NOT Sufficient |
|---|---|---|
| Tests pass | Test command output showing 0 failures | Previous run, "should pass" |
| Build succeeds | Build command exit 0 | Linter passing |
| Bug fixed | Reproduce original symptom: now passes | "Code changed, should work" |
| Regression test works | Red (fail without fix) → Green (pass with fix) | Test passes once |
| Subagent completed task | git diff shows expected changes |
Subagent says "done" |
| Requirements met | Line-by-line checklist against spec | Tests passing |
| Provider dispatch worked | Output contains expected content | No error ≠ success |
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.
- 25d ago Changed · +4 lines 74a949a8d618
- 1mo ago First seen · 144 lines · 20 tokens per session scan A ff144d17ea21
skill-verification-gate is a skill published in the GitHub repository nyldn/claude-octopus (4,320 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,352 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
e2e-testing
End-to-end testing for Falcon Foundry apps using Playwright and @crowdstrike/foundry-playwright. TRIGGER when user asks to "add e2e tests", "add playwright tests", "write end-to-end tests", "test my app", or mentions "e2e", "playwright", or "end-to-end" in the context of testing a Foundry app. DO NOT TRIGGER during…
qa
This skill should be used when running functional QA before merge.
test-browser
This skill should be used when running end-to-end browser tests on pages affected by a PR. Uses agent-browser CLI to map changed files to routes and capture screenshots.
test-fix-loop
This skill should be used when autonomously iterating on test failures: runs the suite, diagnoses, applies minimal fixes, re-runs with checkpoint commit isolation until all tests pass.
eval-harness
This skill provides a promptfoo eval harness that measures whether a Soleur skill or agent edit actually improves behavior, comparing a skill arm against a baseline control arm.
xcode-test
This skill should be used when building and testing iOS apps on the simulator using XcodeBuildMCP. It handles building, installing, launching, screenshot capture, and log analysis for iOS/macOS apps.