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-synthesisgit 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-synthesis)<a href="https://agentmods.dev/skills/abilityai/trinity/dd-synthesis"><img src="https://agentmods.dev/badge/skills/abilityai/trinity/dd-synthesis/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-synthesis"><img src="https://agentmods.dev/badge/skills/abilityai/trinity/dd-synthesis.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 | $0.00033 | $0.00857 |
| Opus 5.5 | $0.00013 | $0.00343 |
| Sonnet 5.5 | $0.00007 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
dd-synthesis 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Source Synthesis Methodology
As the Deal Lead, you must synthesize reports from 9 specialist agents into a coherent narrative and investment recommendation.
Synthesis Process
Step 1: Gather All Reports
Collect reports from shared folders:
/shared-out/founder-analysis/
/shared-out/market-analysis/
/shared-out/competitor-analysis/
/shared-out/tech-analysis/
/shared-out/bizmodel-analysis/
/shared-out/traction-analysis/
/shared-out/compliance-analysis/
/shared-out/captable-analysis/
/shared-out/legal-analysis/
Step 2: Extract Key Findings
From each report, extract:
- Executive summary headline
- Risk score and top 3 concerns
- Top 3 positive indicators
- Any CRITICAL or HIGH severity red flags
- Unverified claims
Step 3: Identify Patterns
Look for themes across reports:
Corroborating Evidence When multiple specialists cite the same positive or negative:
- Strong team: Founder + Tech + Traction all positive
- Market concern: Market + Competitor + BizModel all flag saturation
Contradictions When specialists disagree:
- Founder says $5M ARR, Traction finds $3M evidence
- Tech says "novel IP", Legal finds prior art
Gaps What wasn't adequately analyzed:
- Missing international market analysis
- No direct customer interviews conducted
Step 4: Build the Narrative
Structure your synthesis as:
-
The Opportunity (1 paragraph)
- What makes this company interesting
- Market timing and positioning
-
The Team (1 paragraph)
- Key strengths and gaps
- Track record and references
-
The Risk Profile (2-3 paragraphs)
- Material risks with evidence
- Mitigating factors
- Unresolved questions
-
The Recommendation (1 paragraph)
- Clear INVEST/PASS/NEGOTIATE stance
- Conditions or terms if applicable
Output Documents
1. Investment Recommendation (JSON)
{
"recommendation": {
"decision": "INVEST | NEGOTIATE | PASS",
"confidence": "HIGH | MEDIUM | LOW",
"conditions": ["condition 1", "condition 2"],
"suggested_terms": {
"valuation_range": "$X-$Y",
"check_size": "$Z",
"special_terms": ["board seat", "pro-rata rights"]
}
},
"synthesis": {
"opportunity_thesis": "Why this could be a great investment",
"primary_risks": ["risk 1", "risk 2", "risk 3"],
"mitigating_factors": ["factor 1", "factor 2"],
"open_questions": ["question 1", "question 2"]
},
"specialist_summary": {
"founder": {"score": 25, "headline": "..."},
"market": {"score": 30, "headline": "..."}
},
"overall_risk_score": 28.5
}
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 · 131 lines · 33 tokens per session scan A 761cd3e1aa93
dd-synthesis is a skill published in the GitHub repository Abilityai/trinity (659 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 857 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.