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 skills/bitflight-devops/hallucination-detector/evaluate-optionsnpx skills add bitflight-devops/hallucination-detector --skill evaluate-optionsgit clone --depth 1 https://github.com/bitflight-devops/hallucination-detectorWhat 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 | $0.00097 | $0.00832 |
| Opus 5 | $0.00048 | $0.00416 |
| Sonnet 5 | $0.00019 | $0.00166 |
| Haiku 4.5 | $0.00010 | $0.00083 |
Grade A, and why
evaluate-options 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate Options
Do not present options to the user without evidence. Every recommendation must be grounded in research, not assertion.
Phase 1: Identify Options
State each candidate option as a concrete, implementable approach. If options are not yet identified, identify them before proceeding.
Phase 2: Launch Parallel Research Agents
Launch one option-researcher agent per option in a single message so they run concurrently. Each agent is defined at .claude/skills/evaluate-options/agents/option-researcher.md.
Pass this exact input block to each agent:
PROBLEM: {problem statement and constraints}
OPTION: {option name and one-sentence description}
OPTION_SLUG: {short-identifier-for-filename}
CONTEXT_PATHS:
- scripts/hallucination-audit-stop.cjs
- {any other relevant file paths or doc URLs}
OUTPUT_PATH: ~/.hd/option-eval-{option-slug}-{YYYYMMDD}.md
Example — evaluating two approaches to sentence splitting:
# Agent 1 task
PROBLEM: Add sentence-level scoring to findTriggerMatches() without breaking the hook contract (stdout must remain empty or valid JSON block).
OPTION: Inline regex splitter — split text on sentence boundaries using /[.!?]\s+/ before iterating trigger patterns
OPTION_SLUG: inline-regex-splitter
CONTEXT_PATHS:
- scripts/hallucination-audit-stop.cjs
- tests/hallucination-audit-stop.test.cjs
- hooks/hooks.json
OUTPUT_PATH: ~/.hd/option-eval-inline-regex-splitter-20260310.md
# Agent 2 task
PROBLEM: Add sentence-level scoring to findTriggerMatches() without breaking the hook contract (stdout must remain empty or valid JSON block).
OPTION: Segmenter API — use Intl.Segmenter with granularity "sentence" to split text before iterating trigger patterns
OPTION_SLUG: intl-segmenter
CONTEXT_PATHS:
- scripts/hallucination-audit-stop.cjs
- tests/hallucination-audit-stop.test.cjs
- hooks/hooks.json
OUTPUT_PATH: ~/.hd/option-eval-intl-segmenter-20260310.md
Each agent answers for its option:
- What does this option do — mechanically, step by step?
- What does it protect against or solve?
- What does it leave unprotected or unsolved?
- What are the failure modes?
- What evidence from the codebase or documentation supports or argues against this option? (cite file paths and line numbers)
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.
- 2d ago First seen · 83 lines · 97 tokens per session scan A cfac43751659
evaluate-options is a skill published in the GitHub repository bitflight-devops/hallucination-detector (7 stars, last pushed 29d ago), licensed MIT. It adds 97 tokens to every session and 832 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
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
prism
Run a PRISM College session — multi-LLM peer review for one-way-door architecture decisions. Triggers on /prism, /prism prepare, /prism refract, /prism inspect, /prism sync, /prism settle, /prism memorialize.
research-guardian
AI 研究品質防護系統。在 AI agent 執行研究任務時，自動進行多重驗證、事實查核、文獻交叉比對、實驗設計檢查，防止幻覺、邏輯錯誤、引用錯誤、與 novelty 誤判。 任何時候 AI 被要求進行以下操作都應觸發本 skill： 生成研究假設、撰寫文獻回顧、設計實驗、分析數據、撰寫論文段落、評估研究結果的 novelty、 進行 systematic review、做 meta-analysis、提出研究方向建議、或任何聲稱「發現」或「創新」的場景。 即使使用者沒有明確要求驗證，只要涉及研究性質的輸出，都應主動啟動防護流程。 本 skill 設計用於整合進 AI agent pipeline，作為研究輸出的品質閘門。.
employment-contract-templates
Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.
risk-metrics-calculation
Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.