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 Momo2323-ui/claude-orchestra --skill hallucination-guardgit clone --depth 1 https://github.com/Momo2323-ui/claude-orchestraWrote 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/momo2323-ui/claude-orchestra/hallucination-guard)<a href="https://agentmods.dev/skills/momo2323-ui/claude-orchestra/hallucination-guard"><img src="https://agentmods.dev/badge/skills/momo2323-ui/claude-orchestra/hallucination-guard/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/momo2323-ui/claude-orchestra/hallucination-guard"><img src="https://agentmods.dev/badge/skills/momo2323-ui/claude-orchestra/hallucination-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00099 | $0.02966 |
| Opus 5 | $0.00049 | $0.01483 |
| Sonnet 5 | $0.00020 | $0.00593 |
| Haiku 4.5 | $0.00010 | $0.00297 |
Grade A, and why
hallucination-guard 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 11d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hallucination Guard — Anti-Hallucination Wrapper for the Orchestra System
"Don't make things up. Assume your work is wrong until you've cross-checked it. Verify before you're confident, and test."
This skill operationalizes that into a mandatory wrapper invoked at every orchestra entry, every handoff, and before every completion claim.
When to use
Invoke automatically:
- Before activating any orchestra (entry gate)
- Before any agent/skill claims
DONE - Before any handoff between orchestras (passing work along)
- Before any user-facing claim of success, completion, or correctness
- When drafting a response that uses phrases like "done", "works", "should pass", "great", "perfect", "looks good"
Do not skip even when the task seems trivial. "Just this once" is rationalization — see Red Flag table below.
The 5 layers of protection
| Layer | Source | What it does |
|---|---|---|
| 1. Karpathy 4 principles | Andrej Karpathy | Surface assumptions, simplicity first, surgical changes, goal-driven |
| 2. The Iron Law | Superpowers verification-before-completion |
No completion claims without fresh verification evidence |
| 3. Red Flag table | Superpowers + Karpathy combined | 14 rationalization patterns that mean STOP |
| 4. ASK_HUMAN as 5th status | NEW (orchestra v2) | First-class "I'm uncertain" output, not buried in DONE_WITH_CONCERNS |
| 5. Evidence requirements | NEXUS Reality Checker | Each completion type requires specific proof artifact |
Layer 1 — Karpathy's 4 principles
Principle 1: Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
- State assumptions explicitly. If uncertain, ASK.
- If multiple interpretations exist, present them — don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
Principle 2: Simplicity First
Minimum code that solves the problem. Nothing speculative.
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.
- 11d ago First seen · 337 lines · 99 tokens per session scan A e1a81fd62cee
hallucination-guard is a skill published in the GitHub repository Momo2323-ui/claude-orchestra (8 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 2,966 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.