Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lhl/realitychecknpx agentmods add skills/lhl/realitycheck/rc-searchWrote 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/lhl/realitycheck/rc-search)<a href="https://agentmods.dev/skills/lhl/realitycheck/rc-search"><img src="https://agentmods.dev/badge/skills/lhl/realitycheck/rc-search.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00480 |
| Opus 5 | $0.00012 | $0.00240 |
| Sonnet 5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
rc-search 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 6d 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
Semantic Search
Search claims and sources using natural language queries. Use when looking for related claims or finding existing analysis.
When This Skill Activates
- "Search for claims about"
- "Find related claims"
- "Look up claims"
Search claims and sources using natural language queries.
Usage
rc-db search "query" --limit 10
# or: uv run python scripts/db.py search "query" --limit 10
Note: Semantic search requires embeddings. If search fails with embedding errors:
- Ensure
sentence-transformersis installed (included in realitycheck dependencies) - Check embedding status:
rc-db embed statusoruv run python scripts/embed.py status - Generate missing embeddings:
rc-db embed generateoruv run python scripts/embed.py generate - Do not set
REALITYCHECK_EMBED_SKIP=1unless you explicitly want to disable embeddings (used for CI/testing)
Options
--domain: Filter by domain (TECH/LABOR/ECON/GOV/SOC/RESOURCE/TRANS/GEO/INST/RISK/META)--limit: Maximum results to return (default: 10)--format: Output format -json(default) ortext--type: Filter by record type (claimorsource)
How It Works
- Convert query to embedding using sentence-transformers
- Find nearest neighbors in the claims/sources vector index
- Return ranked results with similarity scores
Output
Results include:
- Claim/Source ID
- Text (truncated)
- Type, Domain, Evidence Level
- Credence score
- Similarity score
Examples
rc-db search "AI automation labor displacement"
rc-db search "training costs" --domain TECH --limit 5
rc-db search "economic transition" --type claim
Related Skills
rc-statsrc-validate
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.
- 6d ago First seen · 71 lines · 23 tokens per session scan A 9997994de714
rc-search is a skill published in the GitHub repository lhl/realitycheck (41 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 480 once invoked, about $0.0001 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
Deep Research
Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.
document-query
Use when reading, extracting, summarizing, comparing, or answering questions over local or remote documents, code files, PDFs, Office files, HTML/text files, large text-heavy files, and fallback OCR for document images or scans when vision tools are unavailable or insufficient.
military-scout
深入调查，掌握实情，找出问题根因.
data-analysis
Analyze datasets and create visualizations.
Jupyter Live Kernel
Guides notebook-first analysis with reproducible kernels, inspectable data loading, and explicit promotion paths back into durable code.
swot-analysis
Use when analyzing strengths/weaknesses/opportunities/threats, strategic planning, decision-making support, problem diagnosis, or when user mentions 'SWOT', '优劣势分析', '战略分析', '机会威胁', '态势分析', '战略规划', '竞品分析', '技术选型', '方案对比', '风险评估', '项目立项', '决策支持'.