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 beefiker/superloopy --skill superloopy-doctorgit clone --depth 1 https://github.com/beefiker/superloopyWrote 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/beefiker/superloopy/superloopy-doctor)<a href="https://agentmods.dev/skills/beefiker/superloopy/superloopy-doctor"><img src="https://agentmods.dev/badge/skills/beefiker/superloopy/superloopy-doctor.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Anti-Refusal · line 81 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00048 | $0.01684 |
| Opus 5 | $0.00024 | $0.00842 |
| Sonnet 5 | $0.00010 | $0.00337 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
superloopy-doctor 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
superloopy-doctor
SUPERLOOPY DOCTOR ENABLED
Use this skill to prove whether a local Superloopy surface can support the Superloopy loop: repo-local .superloopy/ state, artifact-backed evidence under .superloopy/evidence/, bundled crew agents, hook steering, and the deterministic completion floor. It is read-only by default. Do not mutate plugin config, wrappers, agents, caches, or source files unless the user explicitly asks for repair after seeing the report.
Native Boundary
This is a Superloopy health check, not a generic plugin drift audit.
- Treat
superloopy doctor --scope source --jsonas the source-checkout truth surface andsuperloopy doctor --scope installed --jsonas the machine-local installation truth surface. The JSONscopefield records which verdict contract was used. - Treat loop commands as the behavioral truth surface, but keep their limits clear:
superloopy loop status --json,superloopy loop check,superloopy loop guide --json, and evidence files under.superloopy/evidence/can show current plan and artifact readiness. - Read the installed plugin cache only to identify which Superloopy code the wrapper runs.
- Do not clone external repos, search issue trackers, or compare unrelated harness layouts unless the user separately asks for research.
superloopy doctorreports the plugin root it checked: by default it usessourcescope in a recognized Superloopy checkout andinstalledscope elsewhere. Pin a checkout withsuperloopy doctor --root <checkout> --scope source --json; pin an installed cache withsuperloopy doctor --root <cache> --scope installed --json. Source verdicts still return machine-local diagnostics, butinstalledModelPolicyandwrapperdo not gate source health.
Installed-plugin Authority
installedPluginTruth runs the read-only codex plugin list --json authority probe for superloopy@beefiker; it never infers the installed version from cache directory names. A confirmed version mismatch is informational in source scope, but fails installed scope. Missing Codex, no registered plugin, and invalid authority output are informational and do not fail doctor. Report these four states as current, version_mismatch, not_registered, or authority_unavailable; never repair from this probe without explicit approval.
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 · 86 lines · 48 tokens per session scan A 466dbf7b4216
superloopy-doctor is a skill published in the GitHub repository beefiker/superloopy (108 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,684 once invoked, about $0.0002 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
app-bug-forensics
Use when diagnosing or fixing user-reported application bugs. Guides evidence-backed root-cause analysis from symptoms, screenshots, logs, provider failures, background tasks, storage, or desktop lifecycle behavior through a scoped patch and regression tests.
interactive-state-flow
Use when an interactive flow is laggy, stale, or race-prone because user intent, source state, derived presentation, async IO, scheduling, or background work are mixed. Keep source state prompt, protect the urgent interaction path, and admit async or presentation results only through a freshness-owning boundary.
optimize-python-parallelism
Analyze and, when the task authorizes source optimization, refactor a concrete long-running Python entrypoint containing repeated independent work. Use for explicit Python speedup or parallelization requests and evidence-backed long-running entrypoints; skip ordinary Python edits, test execution alone, short scripts…
dev-bugfix
Use for a concrete defect or regression that needs reproduction, root-cause diagnosis, a fix, and regression validation. Do not trigger for routine localized edits or primarily performance-focused work.
dev-cli-auth-diagnosis
Use when gh, hf, lark-cli, Git/SSH, or another authenticated CLI works in one shell or host but reports missing credentials, cannot refresh or persist authentication, cannot reach its service, or behaves differently inside Codex or across permission profiles, macOS, Windows, WSL, containers, or CI. Diagnose sandbox…
dev-build-optimization
Use to diagnose or improve build speed, cache behavior, bundle size, packaging output, and monorepo task execution.