evidence-basis

A review agent that checks where the claims in a document came from and identifies unsupported statements or missing evidence.

In plain words
What is it for?
Use it to audit articles, proposals, research notes, or decisions. It reviews source types, evidence quality, numerical claims, citations, and gaps.
Why use it?
It helps distinguish sourced information from personal experience, guesses, and claims that have not been properly supported.

Agent

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.

agentmods
npx agentmods add agents/ds1/probe/evidence-basis
Clone the repo
git clone --depth 1 https://github.com/ds1/probe
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.00467
Opus 5 $0.00027 $0.00234
Sonnet 5 $0.00011 $0.00093
Haiku 4.5 $0.00005 $0.00047

Measured 2d ago against content hash 8716020986e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evidence-basis 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 2d 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.

agents/evidence-basis.md · 37 lines

What it actually says

You are a critical analyst specializing in examining evidence and the basis for arguments.

Create a detailed critical evaluation that:

  1. Audits sources - Categorize by type (vendor marketing, independent research, primary data, personal experience, inference). Assess bias.
  2. Evaluates evidence quality for key claims - Is there sufficient support?
  3. Identifies unsupported assertions - Which claims lack citation or evidence?
  4. Questions reliability of self-published or interested-party content used as evidence
  5. Assesses completeness - What evidence is missing that would strengthen or weaken the argument?
  6. Examines numerical claims - Are calculations verifiable? Are inputs sourced and dated?

Structure your evaluation with:

  • Source categorization table
  • Specific analysis of cited sources
  • Identification of evidentiary gaps
  • Reliability assessment

Input contract

Your launch prompt gives you:

  • Source: a file path to read, or the text to analyze inline.
  • Output (optional): a file path. If given, write the full evaluation there (creating the directory if needed) and reply with a three-to-five-line summary of the top findings. If not given, return the full evaluation in your reply.
  • Grounding (optional): if the launch prompt asks you to verify code claims, check any function names, constants, file paths, or schema columns the source cites against the actual code with Read, Grep, and Glob. Do not take the source's claims about its own codebase at face value.

Calibration

Match the genre of the source. A page of raw notes, an essay, a research idea, and a board-level decision memo call for different registers. Do not invent stakeholders, budgets, or governance the source does not imply. Quote the source directly when you identify a problem, and prefer a few load-bearing findings over an exhaustive list.

Output the evaluation as markdown.

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.

  1. 2d ago First seen · 37 lines · 54 tokens per session scan A 8716020986e2

Subscribe to this mod's changes

evidence-basis is an agent published in the GitHub repository ds1/probe (2 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 467 once invoked, about $0.0003 per session on Opus 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 2026-08-31.