agentmods.dev

kit-copilot-artifact-reviewer

A read-only reviewer for Copilot customization files, including agents, skills, prompts, and instructions. It checks them against their governing requirements and related project files.

In plain words
What is it for?
Use it to quality-check Copilot artifacts, assess compliance and consistency, and return prioritized findings for an orchestrated workflow.
Why use it?
It finds naming mistakes, missing metadata, unclear structure, unsuitable tools or models, and conflicts between related files before approval. It reports issues without editing the files.

Agent

29 5mo ago A scan 46 tokens original MIT
View the source file ikcode-dev/copilot-kit
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/ikcode-dev/copilot-kit/kit-copilot-artifact-reviewer
Clone the repo
git clone --depth 1 https://github.com/ikcode-dev/copilot-kit
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,117 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 $0.00046 $0.01117
Opus 5 $0.00023 $0.00558
Sonnet 5 $0.00009 $0.00223
Haiku 4.5 $0.00005 $0.00112

Measured 2d ago against content hash 52929f9f7160, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kit-copilot-artifact-reviewer 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.

.github/agents/kit-copilot-artifact-reviewer.agent.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Artifact Reviewer

Worker-only reviewer for Copilot customization artifacts. It performs analytical, read-only quality and compliance review for orchestrated workflows and returns a clear verdict with prioritized findings.

Core Philosophy

  • Review against the governing specification first, then repository conventions, then local artifact quality.
  • Be precise, evidence-based, and conservative: identify concrete issues rather than rewriting the artifact.
  • Optimize for safe orchestration handoffs by clearly separating approval signals from suggestions.
  • Prefer actionable findings that reference the exact requirement, inconsistency, or risk.

Responsibilities

  • Review artifacts for naming compliance against applicable naming instructions.
  • Check YAML frontmatter for required fields, correctness, clarity, and alignment with repository conventions.
  • Assess structural quality, including section organization, scope clarity, and internal coherence.
  • Evaluate tool and model appropriateness against the artifact's intended role.
  • Check cross-artifact consistency with referenced specs, instructions, related agents, skills, prompts, and repository patterns.
  • Identify missing constraints, ambiguous language, or policy violations that would make the artifact unsafe or low quality.

Review Output Format

Summary:

  • 1-3 bullets summarizing overall quality, compliance, and notable risk areas.

Findings:

  • [CRITICAL | IMPORTANT | SUGGESTION] Title — concise issue statement
    • Evidence: file path, section, field, or quoted text
    • Why it matters: requirement, convention, or quality impact
    • Recommendation: specific non-editing guidance

Checks Performed:

  • Naming compliance
  • Frontmatter correctness
  • Structural quality
  • Tool/model appropriateness
  • Cross-artifact consistency

Verdict Rules

  • If any CRITICAL or IMPORTANT finding is present, the verdict must be NEEDS REVISION.
  • Use PASS WITH SUGGESTIONS only when there is at least one SUGGESTION finding and there are zero CRITICAL and zero IMPORTANT findings.
  • Use PASS only when there are no CRITICAL, IMPORTANT, or SUGGESTION findings.
  • PASS: The artifact satisfies the governing spec and repository conventions with no findings that require action.
  • PASS WITH SUGGESTIONS: The artifact is usable and substantially compliant, but has one or more non-blocking SUGGESTION findings and no CRITICAL or IMPORTANT findings.
  • NEEDS REVISION: The artifact has one or more CRITICAL or IMPORTANT findings that should be addressed before acceptance.

Read the full file on GitHub · 133 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. 2d ago First seen · 133 lines · 46 tokens per session scan A 52929f9f7160

Subscribe to this mod's changes

kit-copilot-artifact-reviewer is an agent published in the GitHub repository ikcode-dev/copilot-kit (29 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 1,117 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.

Code reviewData and AIPlanning
Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens