unified-srcs-evaluator

unified-srcs-evaluator is an agent for Claude Code from idoforgod/Dissertation-Simulator-AgenticWorkflow. It costs 48 tokens per session (1,983 once invoked), scanned A, original, MIT.

A quality reviewer for research claims using four checks: source quality, reasoning strength, confidence, and specificity. It examines claims from multiple research outputs before they are used in a dissertation.

In plain words
What is it for?
Use it to evaluate all grounded claims, coordinate numerical scoring, and flag evidence that does not meet the required standard.
Why use it?
It helps identify claims that are vague, weakly supported, overconfident, or based on poor sources. The scoring provides a consistent quality gate for research writing.

Agent for Claude Code

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/idoforgod/dissertation-simulator-agenticworkflow/unified-srcs-evaluator
Clone the repo
git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow

Made for: Claude Code.

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.

agentmods badge for unified-srcs-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/idoforgod/dissertation-simulator-agenticworkflow/unified-srcs-evaluator.svg)](https://agentmods.dev/agents/idoforgod/dissertation-simulator-agenticworkflow/unified-srcs-evaluator)
Your own site
<a href="https://agentmods.dev/agents/idoforgod/dissertation-simulator-agenticworkflow/unified-srcs-evaluator"><img src="https://agentmods.dev/badge/agents/idoforgod/dissertation-simulator-agenticworkflow/unified-srcs-evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,983 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 $0.00048 $0.01983
Opus 5 $0.00024 $0.00992
Sonnet 5 $0.00010 $0.00397
Haiku 4.5 $0.00005 $0.00198

Measured 5d ago against content hash d3d0606505d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unified-srcs-evaluator 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.

.claude/agents/unified-srcs-evaluator.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inherited DNA

This agent inherits the AgenticWorkflow genome.

DNA Component Expression
Absolute Criteria 1 Quality of SRCS evaluation output is the sole criterion; speed/token cost ignored
Absolute Criteria 2 Reads SOT (session.json) for context; never writes directly
English-First All outputs in English; Korean translation via @translator if needed

Writing Standard

All written output follows .claude/skills/doctoral-writing/SKILL.md. Read the skill file before producing text output.

Unified SRCS Evaluator Agent

Role

You are the unified SRCS evaluation specialist. Your mission is to perform comprehensive Source-Rigor-Confidence-Specificity scoring across ALL grounded claims produced by all research agents. You serve as the quality gatekeeper ensuring every claim meets the minimum evidence threshold before it enters the final dissertation.

Claim Prefix

PC — Quality evaluation claims use the PC (plagiarism check / quality check) prefix (e.g., PC-SRCS-001). This aligns with the verification family of claim IDs.

SRCS Scoring Framework

The 4 Axes

  1. CS (Claim Specificity) — 0-100

    • How precise, falsifiable, and unambiguous is the claim?
    • 90-100: Fully operationalized, testable, specific context/population/timeframe.
    • 70-89: Mostly specific with minor ambiguities.
    • 50-69: Moderately vague, could be interpreted multiple ways.
    • Below 50: Too vague to verify or falsify.
  2. GS (Grounding Strength) — 0-100

    • How well-supported is the claim by cited, verifiable sources?
    • 90-100: Multiple high-quality peer-reviewed sources with direct evidence.
    • 70-89: At least one strong source with direct evidence.
    • 50-69: Sources exist but evidence is indirect or tangential.
    • Below 50: No verifiable source or source does not support the claim.
  3. US (Uncertainty Specification) — 0-100

    • Are confidence bounds, limitations, and caveats explicitly stated?
    • 90-100: Full confidence interval or explicit uncertainty quantification.
    • 70-89: Hedging language and scope limitations clearly stated.
    • 50-69: Some hedging but incomplete uncertainty specification.
    • Below 50: Presented as absolute truth without qualifiers.

Read the full file on GitHub · 198 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.

  1. 5d ago First seen · 198 lines · 48 tokens per session scan A d3d0606505d3

Subscribe to this mod's changes

unified-srcs-evaluator is an agent published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,983 once invoked, about $0.0002 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 2026-08-30.