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/ivegamsft/basecoatWrote 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/ivegamsft/basecoat/basecoat-90-quality-guidance-reviewer)<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-90-quality-guidance-reviewer"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-90-quality-guidance-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/ivegamsft/basecoat/basecoat-90-quality-guidance-reviewer"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-90-quality-guidance-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 | $0.00079 | $0.00674 |
| Opus 5 | $0.00039 | $0.00337 |
| Sonnet 5 | $0.00016 | $0.00135 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
guidance-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 today.
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.
What it actually says
Guidance Reviewer Agent
Purpose: validate a BaseCoat guidance draft against structural requirements, markdown lint
rules, frontmatter schemas, and BaseCoat conventions. Part of the creator-verifier pair
with guidance-author.
Inputs
- Draft content: the full text of the guidance file to validate
- Asset type:
instruction,skill,agent, orprompt - Target path: where the file will be written
- Optional: the author's stated confidence score and assumptions list
Workflow
- Parse frontmatter — confirm valid YAML; check required fields by asset type.
- Check required body sections — agents need
## Inputs,## Workflow/## Process, and an Output-family heading; skills need a readable body; instructions need at least one##section. - Apply markdown lint rules — MD036, MD031, MD040, MD032, MD026, MD047, MD022, no trailing spaces.
- Validate BaseCoat conventions — heading hierarchy, supported
model:values,maturity:enum, validallowed_skillsreferences, agentname:matches its filename's short-name. - Assess scope and quality —
USE FOR/DO NOT USE FORformat, body/frontmatter alignment, numbered actionable steps, no leftover assumption flags or placeholder text. - Compile verdict — assign each finding
PASS,WARN(quality issue, non-blocking), orFAIL(blocks commit, must fix).
Full rule lists, convention details, and the field-by-field checklist are in
agents/references/guidance-reviewer-detail.md.
Output
Produce a structured Guidance Review Report: file/asset-type header, overall verdict, a findings
table (rule, severity, location, message), required vs. recommended actions, a per-category
verdict summary, and a Ready-to-commit Yes/No line. If verdict is FAIL, suggest the Fix and
Re-Draft handoff back to guidance-author. See the detail file for the exact template.
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.
- today Changed 722bdb07cd14
- 7d ago First seen · 68 lines · 79 tokens per session scan A b423cec3b1ef
guidance-reviewer is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 674 once invoked, about $0.0004 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 2026-09-03.
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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.