guidance-reviewer

guidance-reviewer is an agent for Claude Code from ivegamsft/basecoat. It costs 79 tokens per session (674 once invoked), scanned A, original, MIT.

A checker for draft guidance files such as agent, skill, instruction, and prompt files. It validates their YAML header, required sections, Markdown formatting, naming, and project conventions.

In plain words
What is it for?
Use it to validate frontmatter, required headings, Markdown lint rules, supported settings, skill references, naming, and alignment between the file's scope and content.
Why use it?
It catches structural and formatting problems before guidance is committed. This helps ensure the file can be understood and used consistently by the project.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it to validate frontmatter, required headings, Markdown lint rules, supported settings, skill references, naming, and alignment between the file's scope and content.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-90-quality-guidance-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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 guidance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-90-quality-guidance-reviewer/github.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-90-quality-guidance-reviewer)
Your own site
<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.

agentmods 80×15 button for guidance-reviewer

Your own site · 80×15
<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>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00079 $0.00674
Opus 5 $0.00039 $0.00337
Sonnet 5 $0.00016 $0.00135
Haiku 4.5 $0.00008 $0.00067

Measured today against content hash 722bdb07cd14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

agents/basecoat-90-quality-guidance-reviewer.agent.md · 68 lines

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, or prompt
  • Target path: where the file will be written
  • Optional: the author's stated confidence score and assumptions list

Workflow

  1. Parse frontmatter — confirm valid YAML; check required fields by asset type.
  2. 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.
  3. Apply markdown lint rules — MD036, MD031, MD040, MD032, MD026, MD047, MD022, no trailing spaces.
  4. Validate BaseCoat conventions — heading hierarchy, supported model: values, maturity: enum, valid allowed_skills references, agent name: matches its filename's short-name.
  5. Assess scope and qualityUSE FOR/DO NOT USE FOR format, body/frontmatter alignment, numbered actionable steps, no leftover assumption flags or placeholder text.
  6. Compile verdict — assign each finding PASS, WARN (quality issue, non-blocking), or FAIL (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.

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. today Changed 722bdb07cd14
  2. 7d ago First seen · 68 lines · 79 tokens per session scan A b423cec3b1ef

Subscribe to this mod's changes

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.