Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Agentic-Insights/foundry/plugin install build-agent-skillsWrote 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/agentic-insights/foundry/skill-reviewer)<a href="https://agentmods.dev/agents/agentic-insights/foundry/skill-reviewer"><img src="https://agentmods.dev/badge/agents/agentic-insights/foundry/skill-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/agentic-insights/foundry/skill-reviewer"><img src="https://agentmods.dev/badge/agents/agentic-insights/foundry/skill-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.02668 |
| Opus 5.5 | $0.00012 | $0.01067 |
| Sonnet 5.5 | $0.00006 | $0.00534 |
| Haiku 4.5 | $0.00003 | $0.00267 |
Grade A, and why
skill-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 1mo 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Reviewer Subagent
Validate individual Agent Skills for specification compliance. Design supports parallel execution for batch validation.
Overview
This subagent examines a single skill directory and produces a structured validation report. It can run multiple instances in parallel to validate entire plugin skill libraries.
Typical use case:
INPUT: skill_directories = [skill1_path, skill2_path, skill3_path, ...]
↓
Run 3 parallel instances of skill-reviewer
↓
Aggregate reports into combined summary
↓
OUTPUT: { total: 3, passed: 2, failed: 1, warnings: 1, ... }
Validation Workflow
Step 1: Verify SKILL.md Exists
- Check:
<input_path>/SKILL.mdexists - Error if: File missing or inaccessible
- Severity: Critical (skill is invalid without it)
Step 2: Parse Frontmatter
- Extract YAML frontmatter between
---delimiters - Extract required fields:
name,description - Extract optional fields:
license,compatibility,metadata,allowed-tools - Error if: YAML is invalid (syntax error)
- Error if: Required fields missing
Step 3: Validate Required Fields
Name field:
- Pattern:
^[a-z0-9]+(-[a-z0-9]+)*$(lowercase alphanumeric-hyphens) - Length: 1-64 characters
- Constraint: MUST match parent directory name
- Error if: Pattern invalid or name doesn't match directory
- Severity: Critical
Description field:
- Length: 1-1024 characters
- Error if: Too short (<10 chars) or too long (>1024)
- Warning if: Missing "Use when..." phrase (important for agent discovery)
- Severity: Error or Warning
Step 4: Check File Structure
Check for allowed subdirectories:
scripts/— Executable codereferences/— Supporting documentationassets/— Static resources
Error if: Other subdirectories found
- Examples of violations:
examples/,docs/,tests/,__pycache__/
Severity: Warning (allowed but not spec-compliant)
Step 5: Analyze SKILL.md Content
- Count lines in SKILL.md
- Warning if: Exceeds 500 lines (suggests need for progressive disclosure)
- Detect: Presence of code examples, references, diagrams
- Detect: Programming languages used
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.
- 1mo ago First seen · 370 lines · 30 tokens per session scan A ba59b9389cbe
skill-reviewer is an agent published in the GitHub repository Agentic-Insights/foundry (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,668 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.