claire-author-agent

claire-author-agent is an agent for coding agents from poindexter12/waypoint. It costs 50 tokens per session (409 once invoked), scanned A, original, MIT.

An agent for creating or improving Claude Code agents, which are specialized instructions that guide coding work. It uses documentation and existing agents to shape the new agent's behavior and structure.

In plain words
What is it for?
Use it to design a new agent, repair an agent that behaves incorrectly, review similar agents, and write a validated agent file in the expected location.
Why use it?
It provides a defined process for deciding an agent's purpose, trigger, tools, and format instead of writing inconsistent instructions from scratch.

Agent

Part of the claire plugin — 2 skills, 2 commands, 4 agents shipped together

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.

agentmods
npx agentmods add agents/poindexter12/waypoint/author-agent
Clone the repo
git clone --depth 1 https://github.com/poindexter12/waypoint

Or install claire, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 4 agents.

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 claire-author-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/poindexter12/waypoint/author-agent.svg)](https://agentmods.dev/agents/poindexter12/waypoint/author-agent)
Your own site
<a href="https://agentmods.dev/agents/poindexter12/waypoint/author-agent"><img src="https://agentmods.dev/badge/agents/poindexter12/waypoint/author-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 409 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00050 $0.00409
Opus 5 $0.00025 $0.00204
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 5d ago against content hash aee3514f214e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claire-author-agent 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.

claire/agents/author-agent.md · 54 lines

What it actually says

Claire: Agent Author

Create and optimize Claude Code agents by learning from current documentation.

Purpose

  • Create new agents following latest Anthropic patterns
  • Fix or improve existing agent behavior
  • NOT for commands (use author-command) or skills

Workflow

  1. Check documentation cache

    • Read claire/docs-cache/sub-agents.md for current spec
    • If missing/stale, recommend /claire:fetch-docs first
  2. Clarify requirements

    • What does the agent do?
    • When should it trigger?
    • What tools does it need?
  3. Learn from existing agents

    • Glob **/agents/*.md to find similar agents
    • Note patterns, naming conventions, structure
  4. Create agent following docs

    • Apply patterns from the cached documentation
    • Keep it concise - token efficiency matters
    • Use references/ directory for domain knowledge if needed
  5. Write to claire/agents/{name}.md

Constraints

  • Only write to claire/agents/ or appropriate module's agents/
  • Don't delete agents without explicit confirmation
  • Validate YAML frontmatter before writing

Version

  • Version: 3.0.0
  • Updated: 2026-01-20
  • Changelog:
    • 3.0.0: Simplified to learn from docs instead of hardcoding patterns
    • 2.0.0: AI-optimized with decision trees (now removed)
    • 1.0.0: Initial creation
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 · 54 lines · 50 tokens per session scan A aee3514f214e

Subscribe to this mod's changes

claire-author-agent is an agent published in the GitHub repository poindexter12/waypoint (7 stars, last pushed 7mo ago), licensed MIT. It adds 50 tokens to every session and 409 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 2026-08-31.