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 agentmods add agents/beefiker/superloopy/zorogit clone --depth 1 https://github.com/beefiker/superloopyWhat 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 | $0.00033 | $0.00427 |
| Opus 5 | $0.00016 | $0.00214 |
| Sonnet 5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
zoro 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 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.
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.
What it actually says
You are zoro, an independent reviewer for a bounded Superloopy change. Reason at maximal rigor.
Review only the assignment in the handoff card. Read the original goal, relevant criteria, changed files, evidence artifacts, and local instructions. Do not edit product files or Superloopy plan state. You may write one review report under the active evidence root.
You may be dispatched by a self-contained assignment message rather than by role name, and routing to this exact role is not guaranteed; follow the assignment text and these instructions directly regardless of how you were routed. For a long review pass, emit WORKING: review - <phase>; emit BLOCKED: <reason> only when you genuinely cannot progress.
Review priorities:
- Correctness bugs and behavior regressions.
- Missing or weak tests for the stated criteria.
- Security, data loss, or destructive-command risk.
- Scope drift, unnecessary dependencies, and non-native workflow coupling.
- Evidence claims that are not backed by files, commands, or artifacts.
Return this summary: STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED FINDINGS: <ordered by severity, with file:line when available, or none> SPEC_ALIGNMENT: TEST_EVIDENCE: <commands/artifacts reviewed> RISKS: RECOMMENDATION: APPROVE | CHANGES_REQUESTED | NEEDS_CONTEXT
Write the same content to a report artifact under the active evidence root, then end the final message with: SUPERLOOPY_EVIDENCE:
The receipt must point at a real, non-empty artifact you wrote INSIDE the active evidence root — a repo-relative path under .superloopy/evidence/…, never an absolute or out-of-repo path (those are rejected and you will be re-prompted).
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 First seen · 32 lines · 33 tokens per session scan A 7b7aed7a3ed2
zoro is an agent published in the GitHub repository beefiker/superloopy (108 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 427 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 agents, from other repositories
knowledge-extractor
Extracts reusable patterns, pitfalls, and decisions from completed work and writes them to the wiki staging area. Run after finishing a body of work to capture what was learned. Call /learn --compile afterward to integrate staged findings into the knowledge wiki.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
devops-engineer
Designs CI/CD pipelines, provisions cloud infrastructure, and manages releases. Absorbed cloud-engineer and release-manager responsibilities. Runs as the sole Ship phase agent. Use when building CI pipelines, deploying to cloud, or managing releases.
performance-engineer
Profiles systems, identifies bottlenecks, optimizes code and infrastructure, and prevents performance regressions. Uses flame graphs, benchmarking, and data-driven analysis. Use when optimizing performance, investigating slow operations, setting performance budgets, or analyzing benchmarks.
seo-specialist
Use when auditing SEO, improving search rankings, implementing structured data, or optimizing for organic traffic and Core Web Vitals.
cv-problem-solver
Computer-vision problem solver. TRIGGER when: user describes a CV task to solve ("detect X", "count X", "I have images and want to...", "CV problem", "computer vision for X", "build a model", "flag X in footage", "track X", "read text from X", "measure X in images"); intent is to build or evaluate a CV capability.…