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 skills/dormstern/forge/evidence-weightingnpx skills add dormstern/forge --skill evidence-weightinggit clone --depth 1 https://github.com/dormstern/forgeWrote 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/dormstern/forge/evidence-weighting)<a href="https://agentmods.dev/skills/dormstern/forge/evidence-weighting"><img src="https://agentmods.dev/badge/skills/dormstern/forge/evidence-weighting.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01426 |
| Opus 5 | $0.00000 | $0.00713 |
| Sonnet 5 | $0.00000 | $0.00285 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade A, and why
evidence-weighting 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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Weighting & Confidence Scoring
Evidence is the currency of Founder mode. Confidence scores are denominated in evidence — and the rubric is brutal because most founders inflate confidence on stated intent and call it validated.
The three evidence weights
| Weight | What qualifies |
|---|---|
| 3 — Behavioral | Past actions. Artifacts shown. Commitments made. Money spent. Workarounds built. Tools currently used. The interviewee did something. |
| 2 — Mixed | Some past behavior, partially vague. "We've thought about this several times" → maybe behavioral, maybe imagined. "I tried [X] last year" but no detail on outcome. |
| 1 — Stated intent | "I would use it." "Sounds useful." "I'd pay for that." "We're planning to do this." Pure speculation about future behavior. |
The hardest rule: future intent is NEVER weight 3. Even if the interviewee is enthusiastic. Even if they "really mean it." Past behavior > stated intent. Always.
What weight 3 actually looks like
- "I built a Python script three months ago to do this manually. Want to see it?" (artifact + past action)
- "We pay [Vendor] $40K/year for this. The contract is in renewal in March." (money spent + commitment)
- "I switched from [Tool A] to [Tool B] in January because [Tool A] couldn't handle [problem]. Here's the migration log." (past action + reason + artifact)
- "I've been emailing this to my team every Monday for the last 8 months." (workaround + frequency)
What weight 1 actually looks like
- "I would absolutely use that."
- "That sounds like something I'd pay for."
- "We need a tool exactly like this."
- "Yes, this is a major problem in our industry."
- "Everyone I know would use this."
If you're nodding along when you read those, you're seeing why this rule exists. They feel persuasive in the moment. They mean nothing.
Confidence scoring rubric (1–5)
| Score | Label | Evidence required |
|---|---|---|
| 1 | Speculation | None — gut feel only |
| 2 | Weak Signal | 1–3 data points, single source type |
| 3 | Moderate Evidence | 4–7 data points, multiple source types, contradictions addressed |
| 4 | Strong Evidence | 8–12 data points, diverse sources, contradictions explained or refuted |
| 5 | Validated | 13+ data points, behavioral evidence, commitments obtained |
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.
- 5d ago First seen · 106 lines · 0 tokens per session scan A d5416d42d47b
evidence-weighting is a skill published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,426 tokens. 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…