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 Abilityai/trinity --skill dd-verificationgit clone --depth 1 https://github.com/Abilityai/trinityWrote 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/abilityai/trinity/dd-verification)<a href="https://agentmods.dev/skills/abilityai/trinity/dd-verification"><img src="https://agentmods.dev/badge/skills/abilityai/trinity/dd-verification/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/abilityai/trinity/dd-verification"><img src="https://agentmods.dev/badge/skills/abilityai/trinity/dd-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00582 |
| Opus 5.5 | $0.00014 | $0.00233 |
| Sonnet 5.5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
dd-verification 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.
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.
Claim Verification Methodology
When analyzing claims from pitch decks, founder statements, or company materials, follow this rigorous verification process.
Verification Levels
Assign one of these confidence levels to every claim:
| Level | Definition | Requirements |
|---|---|---|
| VERIFIED | Confirmed via 2+ independent sources | Multiple credible sources agree |
| PARTIALLY VERIFIED | Some evidence supports, gaps remain | One credible source + logical consistency |
| UNVERIFIED | Cannot confirm with available data | No independent sources found |
| CONTRADICTED | Evidence conflicts with claim | Sources disagree with stated claim |
Verification Process
1. Identify the Claim
Extract the specific, testable assertion:
- ❌ "We're growing fast" (vague)
- ✅ "We grew 300% YoY in 2024" (specific, testable)
2. Find Independent Sources
Never rely solely on company-provided materials. Seek:
- Public filings (SEC, state records)
- Third-party data providers (Crunchbase, PitchBook, LinkedIn)
- Press coverage (with dates)
- Customer reviews and testimonials
- Industry reports from analysts
3. Cross-Reference
Compare across sources:
- Do numbers align within reasonable variance (±10%)?
- Are timelines consistent?
- Do different sources tell the same story?
4. Document Everything
For each verified claim, record:
{
"claim": "The specific claim text",
"confidence": "VERIFIED | PARTIALLY VERIFIED | UNVERIFIED | CONTRADICTED",
"sources": [
{"name": "Source name", "url": "URL if available", "date": "YYYY-MM-DD"}
],
"notes": "Any caveats or context"
}
Red Flags
Watch for these warning signs:
- Round numbers without context ("$10M ARR exactly")
- Claims that can't be independently verified
- Metrics that don't match industry standards
- Vague timeframes ("recently", "soon")
- Comparisons without clear methodology
Output Format
Include a verification summary in your analysis:
{
"verification_summary": {
"total_claims_analyzed": 15,
"verified": 8,
"partially_verified": 4,
"unverified": 2,
"contradicted": 1
},
"key_concerns": [
"Market size claim contradicted by industry reports",
"Founder employment dates don't match LinkedIn"
]
}
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 · 83 lines · 35 tokens per session scan A 992824df201a
dd-verification is a skill published in the GitHub repository Abilityai/trinity (665 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 582 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
skill-build
Canonical Runx skill-authoring implementation. Use for designing, creating, updating, improving, or adding harness coverage to a Runx skill package; it combines bounded agent judgment with native file writes, inspection, and safe harness validation. When a host skill-creator also triggers, use its general guidance but…
operations-review
Operate a project, workspace, or account from an agent or manager dashboard: inspect state, triage risks, prepare governed actions, route to the right skill lane, require approvals for consequential acts, and verify receipts after execution.
receipt-audit
Audit a sealed runx receipt for governance, comparing exercised authority and any declared approval requirement with signed evidence, and flag over-reach, approval inconsistency, unrecorded refusals, or exposed secret material.
receipt-query
Retrieve bounded receipt evidence by exact ids or explicit filters, returning native verification results for downstream review.
message-send
Send one digest-bound message on behalf of a principal, posting to a channel or replying in a bound conversation through a compatible connector, after exact approval and independent provider readback.
web-fetch
Fetch and extract one public web source, optionally restrict its hosts, and return the content by digest with full provenance.