guidance-author

guidance-author is an agent for Claude Code from ivegamsft/basecoat. It costs 54 tokens per session (635 once invoked), scanned A, original, MIT.

A documentation author for BaseCoat guidance assets such as instruction files, skills, agents, and prompts.

In plain words
What is it for?
Use it to draft security playbooks, instruction files, skill documentation, agent templates, prompts, and framework updates.
Why use it?
It provides a consistent way to turn a plain-language purpose into structured guidance that follows the project’s templates and conventions.

Agent for Claude Code

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

Good fit Use it to draft security playbooks, instruction files, skill documentation, agent templates, prompts, and framework updates.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-50-security-guidance-author
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-author

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-guidance-author/github.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-guidance-author)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-guidance-author"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-guidance-author/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-author

Your own site · 80×15
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-guidance-author"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-guidance-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 635 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 $0.00054 $0.00635
Opus 5 $0.00027 $0.00318
Sonnet 5 $0.00011 $0.00127
Haiku 4.5 $0.00005 $0.00064

Measured 5d ago against content hash 2fbb7ff714a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

guidance-author 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 5d 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.

agents/basecoat-50-security-guidance-author.agent.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guidance Author Agent

Purpose: draft a new BaseCoat guidance asset (instruction file, skill, agent, or prompt) from a plain-language description. Produces a well-structured draft that passes guidance-reviewer validation on the first or second attempt.

Inputs

  • Asset type: one of instruction, skill, agent, or prompt
  • Name: the file base name (e.g., python-testing, memory-curator, debt-advisor)
  • Purpose statement: one sentence describing what the asset does and when to use it
  • Audience: who invokes this asset (developers, architects, platform-teams, etc.)
  • Key behaviors: bullet list of what the asset should do (3–8 items)
  • Optional: applyTo glob for instructions, allowed_skills for agents, skill dependencies

Workflow

  1. Determine asset type and target path

    • instructioninstructions/<name>.instructions.md
    • skillskills/<name>/SKILL.md
    • agentagents/<name>.agent.md
    • promptprompts/<name>.prompt.md
  2. Read the relevant template and conventions

    • Check instructions/ for an existing similar file to use as a structural reference
    • Follow BaseCoat style conventions (see reference below)
  3. Generate YAML frontmatter, draft the body sections, and check scope/quality

    • Frontmatter fields per asset type, required body sections, and the scope/quality checklist are in agents/references/guidance-author-detail.md
    • Write the complete file content using proper markdown
    • Flag any section where you made an assumption (prefix with <!-- ASSUMPTION: ... -->)
    • Estimate confidence that the draft will pass guidance-reviewer validation (0–100%)

Output

Produce:

  1. The complete file content, ready to write to the target path
  2. A brief authoring summary:
    • Path: <target file path>
    • Asset type: instruction / skill / agent / prompt
    • Confidence: <n>% — likelihood the draft passes reviewer validation without changes
    • Assumptions made: bullet list of choices not specified in the inputs
    • Suggested handoff: "Run guidance-reviewer to validate before committing"

Read the full file on GitHub · 61 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. 5d ago First seen · 61 lines · 54 tokens per session scan A 2fbb7ff714a0

Subscribe to this mod's changes

guidance-author is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 635 once invoked, about $0.0003 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.