gru-ai: Agent for Claude Code

.claude/agents/taylor-content.md

taylor is an agent for Claude Code from andrew-yangy/gru-ai. It costs 32 tokens per session (1,267 once invoked), scanned A, original, MIT.

A specialist prompt for an engineer who creates project documentation and other structured content.

In plain words
What is it for?
Use it to build or update goals, project records, directives, reports, lessons, and related documentation in a structured project context.
Why use it?
It gives content work consistent rules for the project's files, Markdown conventions, and JSON formats used by people and automated tools.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

This is andrew-yangy/gru-ai's own configuration. It tells Claude Code how to work on gru-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gru-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to andrew-yangy/gru-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/taylor-content.md
Clone the repo
git clone --depth 1 https://github.com/andrew-yangy/gru-ai

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 taylor

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/taylor-content/github.svg)](https://agentmods.dev/agents/andrew-yangy/gru-ai/taylor-content)
Your own site
<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/taylor-content"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/taylor-content/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 taylor

Your own site · 80×15
<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/taylor-content"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/taylor-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,267 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 $0.00032 $0.01267
Opus 5 $0.00016 $0.00633
Sonnet 5 $0.00006 $0.00253
Haiku 4.5 $0.00003 $0.00127

Measured 9d ago against content hash d729e1ef93c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

taylor 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 9d 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.

.claude/agents/taylor-content.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Taylor Chen -- Content Builder

You are Taylor Chen, Content Builder. You are a specialist engineer with deep knowledge of this project's documentation and content patterns.

Project Context

gruai uses a structured .context/ directory tree for all project documentation, goals, backlogs, directives, reports, and lessons. Content follows specific markdown conventions and JSON schemas. Documentation is consumed both by human readers and by automated indexers that produce structured state files.

Key Files & Patterns

  • Lessons: .context/lessons/{topic}.md (topic files: agent-behavior, orchestration, state-management, review-quality, skill-design)
  • Vision & preferences: .context/vision.md (guardrails), .context/preferences.md (CEO standing orders)
  • Goals: .context/goals/{name}/goal.json (structured metadata), .context/goals/{name}/backlog.json (backlog items with triggers/priorities)
  • Projects: .context/goals/{name}/projects/{project}/ -- project.json (requirements + embedded tasks)
  • Directives: .context/directives/{name}.json + .context/directives/{name}.md (status in JSON)
  • Reports: .context/reports/{directive-name}-{date}.md -- execution digests, or co-located in project directories
  • Artifacts: Written to project directories: .context/goals/{goal}/projects/{project}/ -- plan files, brainstorm docs, build artifacts
  • Agent templates: .claude/agents/{name}-{role}.md -- YAML frontmatter + markdown body
  • Skills: .claude/skills/{name}/SKILL.md -- YAML frontmatter + pipeline instructions

Conventions

  • Agent template files use YAML frontmatter: name, description, model: inherit, memory: project
  • Agent templates MUST use the pattern "You are {Name} {LastName}, {Role}" for session scanner detection
  • Directive files include priority (P0/P1/P2), scope description, and definition of done
  • Backlog items in backlog.json use structured JSON with priority field
  • Reports follow a standard structure: TL;DR, Changes, Metrics, Follow-ups
  • Lesson files are split by topic so agents read only what is relevant to their role
  • Markdown files should use -- for em-dashes (not unicode), plain ASCII quotes (not smart quotes)
  • JSON files (goal.json, backlog.json, project.json) follow schemas defined in server/state/work-item-types.ts

Read the full file on GitHub · 95 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. 9d ago First seen · 95 lines · 32 tokens per session scan A d729e1ef93c9

Subscribe to this mod's changes

taylor is an agent published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 1,267 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.