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-validateWrote 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-validate)<a href="https://agentmods.dev/skills/lhl/realitycheck/rc-validate"><img src="https://agentmods.dev/badge/skills/lhl/realitycheck/rc-validate/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/lhl/realitycheck/rc-validate"><img src="https://agentmods.dev/badge/skills/lhl/realitycheck/rc-validate.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 | $0.00022 | $0.00397 |
| Opus 5.5 | $0.00009 | $0.00159 |
| Sonnet 5.5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
rc-validate 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 1mo 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
Data Validation
Validate Reality Check database integrity and referential consistency. Run after adding data or before committing.
When This Skill Activates
- "Validate the database"
- "Check data integrity"
- "Run validation"
Validate Reality Check database integrity and referential consistency.
Usage
rc-validate
# or: uv run python scripts/validate.py
Options
--strict: Fail on warnings (not just errors)--json: Output results as JSON--fix: Attempt to auto-fix simple issues (use with caution)
Checks Performed
- Schema validation - All records match expected schema
- ID format - Claim IDs match
DOMAIN-YYYY-NNNformat - Referential integrity - All source_ids point to existing sources
- Embedding completeness - All records have vector embeddings
- Required fields - No missing required fields
- Duplicate detection - No duplicate IDs
Output
Validation Results:
- Claims: 42 checked, 0 errors, 1 warning
- Sources: 15 checked, 0 errors, 0 warnings
- Chains: 3 checked, 0 errors, 0 warnings
- Predictions: 8 checked, 0 errors, 0 warnings
Status: OK (1 warning)
When to Run
- After adding new claims/sources
- Before committing data changes
- As part of CI/CD pipeline
- When debugging data issues
Related Skills
checkrc-stats
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.
- 1mo ago First seen · 69 lines · 22 tokens per session scan A e34ce5b4b9bd
rc-validate is a skill published in the GitHub repository lhl/realitycheck (44 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 397 once invoked, about $0.0001 per session on Opus 5.5. 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
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
document-query
Read, extract or compare PDFs, Office files, URLs and large text; OCR when vision fails.
docsite-link-sweep
Sweep the googleapis/mcp-toolbox docs for broken and non-canonical links, report each finding with its cause, and apply the safe class of internal link fixes. CI does not check links on this repo, so this skill is the only link check that runs. Use when a maintainer asks for a link sweep or a docs health check, before…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.