A source-tracking standard for due-diligence reports, where due diligence means investigating a company or investment before making a decision. It defines source quality levels and the citation details to record for each finding.

Use it when documenting findings from filings, government databases, company records, interviews, news, data providers, research, or social media.

It makes claims traceable, easier to verify later, and more defensible in audits or legal reviews. It also helps distinguish primary records, established reporting, and less reliable sources.

dd-sourcing — Skill for Claude Code and Codex by Abilityai/trinity

Install

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.

Any agent

npx skills add Abilityai/trinity --skill dd-sourcing

Clone the repo

git clone --depth 1 https://github.com/Abilityai/trinity

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/abilityai/trinity/dd-sourcing/github.svg)](https://agentmods.dev/skills/abilityai/trinity/dd-sourcing)

Your own site

<a href="https://agentmods.dev/skills/abilityai/trinity/dd-sourcing"><img src="https://agentmods.dev/badge/skills/abilityai/trinity/dd-sourcing/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/abilityai/trinity/dd-sourcing"><img src="https://agentmods.dev/badge/skills/abilityai/trinity/dd-sourcing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 648 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00029	$0.00648
Opus 5.5	$0.00012	$0.00259
Sonnet 5.5	$0.00006	$0.00130
Haiku 4.5	$0.00003	$0.00065

Measured 1mo ago against content hash f033a751adb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dd-sourcing 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.

docs/demos/vc-due-diligence/skills/dd-sourcing/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Documentation Standards

All due diligence findings must be traceable to their sources. This enables audit trails, follow-up verification, and legal defensibility.

Source Quality Tiers

Tier 1: Primary Sources (Highest Credibility)

SEC filings (10-K, 10-Q, S-1)
Court documents and legal filings
Government databases (USPTO, state registrations)
Company's own audited financials
Direct customer/reference interviews

Tier 2: Secondary Sources (High Credibility)

Established data providers (Crunchbase, PitchBook, CB Insights)
Major news outlets (WSJ, Bloomberg, TechCrunch)
Industry analyst reports (Gartner, Forrester)
LinkedIn profiles (for employment verification)
Academic research and papers

Tier 3: Tertiary Sources (Use with Caution)

Social media posts
Blog articles
Glassdoor reviews
Wikipedia (only as starting point)
Forum discussions

Citation Format

Every fact must include a source citation:

{
  "source": {
    "name": "Full source name",
    "type": "SEC_FILING | NEWS | DATA_PROVIDER | INTERVIEW | GOVERNMENT | OTHER",
    "url": "https://... (if available)",
    "access_date": "2024-01-15",
    "publication_date": "2024-01-10",
    "tier": 1,
    "excerpt": "Relevant quote or data point"
  }
}

Best Practices

DO:

Capture URLs at time of access (pages change/disappear)
Note the access date for all web sources
Quote relevant passages, don't just link
Use multiple sources for critical claims
Prefer recent sources over older ones

DON'T:

Cite a source you haven't actually reviewed
Use company press releases as independent verification
Rely on a single source for material claims
Cite sources behind paywalls without noting limitation
Mix up "stated by company" vs "independently verified"

Source Tracking in Output

Include a sources section in every analysis:

{
  "sources_used": [
    {
      "id": "S1",
      "name": "Crunchbase - Acme Corp Profile",
      "url": "https://crunchbase.com/...",
      "access_date": "2024-01-15",
      "tier": 2,
      "used_for": ["funding_history", "employee_count"]
    }
  ],
  "source_statistics": {
    "tier_1": 3,
    "tier_2": 8,
    "tier_3": 2,
    "total": 13
  }
}

Read the full file on GitHub · 99 lines

Changes

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 · 99 lines · 29 tokens per session scan A f033a751adb6

Subscribe to this mod's changes

dd-sourcing is a skill published in the GitHub repository Abilityai/trinity (659 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 648 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.

Research agent-orchestration agent-runtime agentic-ai ai-agent ai-agents ai-governance

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…

runxhq/runx · 71 tokens

dd-sourcing