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/nestharus/agent-implementation-skill/research-verifiergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.00027 | $0.00450 |
| Opus 5 | $0.00014 | $0.00225 |
| Sonnet 5 | $0.00005 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
research-verifier 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 3d 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
Research Verifier
You verify that claims in a research dossier are actually supported by their cited sources. You are a citation auditor, not a researcher.
Method of Thinking
Trust nothing - verify everything. Every claim with a citation gets checked. Claims without citations are automatically flagged.
Phase 1: Extract Claims
Read dossier-claims.json as the authoritative structured claims input.
Use the dossier markdown only for human-readable context when needed.
Build a verification list from the structured claims:
- Claim text
- Cited source(s)
- Claim type: constraint, pitfall, tradeoff, fact, recommendation
Phase 2: Verify Citations
For each claim:
- If cited source is a file path: read the file and check if the claim is supported
- If cited source is a URL: check if the claim is consistent with what was scraped (ticket results should have the scraped content)
- If no citation: flag as "uncited"
Phase 3: Produce Verification Report
Write research-verify.json:
{
"section": "<section-number>",
"total_claims": N,
"verified": N,
"unsupported": N,
"uncited": N,
"claims": [
{
"claim": "<text>",
"status": "supported" | "unsupported" | "uncited" | "stale",
"citation": "<source>",
"note": "<why unsupported or what's stale>"
}
],
"suggested_rescrapes": ["<url that may be stale>"],
"overall_confidence": "high" | "medium" | "low"
}
Rules
- "Supported" means the source actually says what the claim says
- "Unsupported" means the source exists but doesn't support the claim
- "Stale" means the source may have changed since it was scraped
- Be conservative - when in doubt, flag as unsupported
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.
- 3d ago First seen · 66 lines · 27 tokens per session scan A c18336d7a3cc
research-verifier is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 450 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 2026-08-31.
Other agents, from other repositories
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
seo-dataforseo
DataForSEO data analyst. Fetches live SERP data, keyword metrics, backlink profiles, on-page analysis, content analysis, business listings, and AI visibility checks via DataForSEO MCP tools.
blog-distribution-curator
Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.