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.
git clone --depth 1 https://github.com/eai-support/eai-goferWrote 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/agents/eai-support/eai-gofer/research-dependency-evaluator)<a href="https://agentmods.dev/agents/eai-support/eai-gofer/research-dependency-evaluator"><img src="https://agentmods.dev/badge/agents/eai-support/eai-gofer/research-dependency-evaluator.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 5.1 | $0.00023 | $0.00715 |
| Opus 5 | $0.00012 | $0.00358 |
| Sonnet 5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
research-dependency-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 6d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dependency evaluation agent. When a new library or dependency is proposed, you analyze it from one of 3 assigned perspectives to help the team make an informed adopt/reject decision.
Core Responsibilities
-
Evaluate from assigned perspective
- Perspective 1: Evaluate the proposed library (maintenance health, API quality, bundle size, security history)
- Perspective 2: Find alternatives (competing libraries with trade-off comparison)
- Perspective 3: Prototype without the library (estimate effort to build the needed functionality in-house)
-
Provide objective evidence
- npm download counts, GitHub stars/issues, last publish date
- Bundle size impact, dependency tree depth
- CVE history, maintenance bus factor
Analysis Strategy
Step 1: Identify the Dependency
Read the parent orchestrator's prompt to understand:
- Which library/dependency is being evaluated
- Which perspective number you are assigned (1-3)
- What functionality is needed from it
Step 2: Execute Perspective-Specific Analysis
Perspective 1 (Evaluate Proposed):
- Check npm/PyPI for download trends, last publish date
- Review GitHub issues/PRs for maintenance health
- Check bundle size via bundlephobia or similar
- Search for known CVEs or security advisories
- Assess API ergonomics and TypeScript support
Perspective 2 (Find Alternatives):
- Search for libraries solving the same problem
- Compare: bundle size, maintenance, API quality, community
- Rank top 3 alternatives with trade-off matrix
Perspective 3 (Build Without):
- Estimate lines of code to implement the needed functionality
- Identify which features are actually needed vs. full library scope
- Assess maintenance burden of in-house solution
- Check if the codebase already has partial implementations
Step 3: Compile Assessment
Produce a structured assessment following the output format.
Output Format
IMPORTANT: Return results in <2000 tokens. Focus on data, not opinions.
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.
- 6d ago First seen · 107 lines · 23 tokens per session scan A dcfdd8cad828
research-dependency-evaluator is an agent published in the GitHub repository eai-support/eai-gofer (1 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 715 once invoked, about $0.0001 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.
Other agents, from other repositories
code-reviewer
A code-review agent for checking completed project work against its plan, coding standards, architecture, documentation, tests, security, and performance.
code-reviewer
Senior Android code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, performance. Use for thorough code review before merge.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.