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-report-formatgit 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-report-format)<a href="https://agentmods.dev/skills/abilityai/trinity/dd-report-format"><img src="https://agentmods.dev/badge/skills/abilityai/trinity/dd-report-format/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-report-format"><img src="https://agentmods.dev/badge/skills/abilityai/trinity/dd-report-format.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 | $0.00027 | $0.00757 |
| Opus 5.5 | $0.00011 | $0.00303 |
| Sonnet 5.5 | $0.00005 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
dd-report-format 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Due Diligence Report Format
All specialist agents must output their analysis in this standardized JSON format. This enables automated synthesis by the Deal Lead agent.
Standard Report Structure
{
"metadata": {
"agent": "dd-{specialist}",
"company": "Company Name",
"analysis_date": "2024-01-15T10:30:00Z",
"version": "1.0"
},
"executive_summary": {
"headline": "One-sentence assessment",
"recommendation": "POSITIVE | NEUTRAL | NEGATIVE | CRITICAL",
"confidence": "HIGH | MEDIUM | LOW",
"key_findings": [
"Finding 1",
"Finding 2",
"Finding 3"
]
},
"risk_assessment": {
"overall_score": 35,
"category_scores": {
"category_name": {
"score": 30,
"weight": 0.25,
"rationale": "Brief explanation"
}
},
"red_flags": [
{
"severity": "HIGH | MEDIUM | LOW",
"description": "Description of the red flag",
"evidence": "Supporting evidence",
"mitigation": "Possible mitigation or none"
}
],
"green_flags": [
{
"description": "Positive indicator",
"evidence": "Supporting evidence"
}
]
},
"detailed_analysis": {
"section_name": {
"findings": "Detailed analysis text",
"data": {},
"sources": ["S1", "S2"]
}
},
"sources": [
{
"id": "S1",
"name": "Source name",
"url": "URL",
"tier": 1,
"access_date": "2024-01-15"
}
],
"verification_summary": {
"total_claims": 15,
"verified": 10,
"partially_verified": 3,
"unverified": 1,
"contradicted": 1
},
"follow_up_items": [
{
"priority": "HIGH | MEDIUM | LOW",
"description": "Item requiring further investigation",
"assigned_to": "dd-{specialist} or HUMAN"
}
]
}
Risk Scoring
Use a 0-100 scale where:
- 0-20: Minimal risk (green light)
- 21-35: Low risk (proceed with standard diligence)
- 36-50: Moderate risk (proceed with caution)
- 51-70: High risk (significant concerns)
- 71-100: Critical risk (major red flags)
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 · 126 lines · 27 tokens per session scan A 5718b0c7b956
dd-report-format is a skill published in the GitHub repository Abilityai/trinity (659 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 757 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
dispute-respond
Prepare and explicitly file an evidence-bound payment dispute response using native receipt proof, approval, provider execution, and independent readback.
purchase-approval
Decide whether one proposed purchase is allowed under an explicit procurement policy before any spend flow starts, refusing budget overages and unapproved vendors instead of guessing.
pay
Pay one external payment requirement within exact parent authority, through a payment method the payer holds, and read the paid resource back.
charge
Quote, then verify and settle, one buyer's payment for a resource you sell, with approval and provider readback.
refund
Refund all or part of one settled payment on its original rail, with approval, idempotency, and readback.
settle-invoice
Check one invoice against the authority that may pay it, then pay it through pay with approval and readback.