carve-harness: Agent for Claude Code

.claude/agents/fable-researcher.md

fable-researcher is an agent for Claude Code from claude-code-expert/carve-harness. It costs 88 tokens per session (302 once invoked), scanned A, original, MIT.

An agent for research before implementation, using official documentation and current versions and writing the evidence and links into RESEARCH.md.

In plain words
What is it for?
Use it to check documentation, confirm software versions, and collect implementation guidance before coding.
Why use it?
It reduces the risk of building against outdated information or making technical decisions without supporting sources.

Agent for Claude Code

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

This is claude-code-expert/carve-harness's own configuration. It tells Claude Code how to work on carve-harness 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 carve-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to claude-code-expert/carve-harness. 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/claude-code-expert/carve-harness/main/.claude/agents/fable-researcher.md
Clone the repo
git clone --depth 1 https://github.com/claude-code-expert/carve-harness

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 fable-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/claude-code-expert/carve-harness/fable-researcher.svg)](https://agentmods.dev/agents/claude-code-expert/carve-harness/fable-researcher)
Your own site
<a href="https://agentmods.dev/agents/claude-code-expert/carve-harness/fable-researcher"><img src="https://agentmods.dev/badge/agents/claude-code-expert/carve-harness/fable-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 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 $0.00088 $0.00302
Opus 5 $0.00044 $0.00151
Sonnet 5 $0.00018 $0.00060
Haiku 4.5 $0.00009 $0.00030

Measured 7d ago against content hash b2296b5da405, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fable-researcher 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 7d 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/fable-researcher.md · 24 lines

What it actually says

너는 팀의 리서처다. 조사만 한다 — 코드 구현·수정 금지.

규칙

  • 공식 소스·최신 버전 우선. 모든 수치·버전·주장에 출처 URL을 붙인다.
  • 확인 못 한 내용은 "미확인"으로 명시 표기. 아는 척 금지.
  • 리포 내부 조사는 실제 파일을 열어 확인한다(경로:라인 인용).
  • 산출물은 결론 먼저: 권장안 → 근거 → 대안 → 출처 순.

파일 소유권

.planning/**, docs/research/** — 이 밖에 쓰지 않는다.

완료 보고 형식

핵심 결론 3줄 이내 · 산출 파일 경로 · 미확인/불확실 항목 목록.

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. 7d ago First seen · 24 lines · 88 tokens per session scan A b2296b5da405

Subscribe to this mod's changes

fable-researcher is an agent published in the GitHub repository claude-code-expert/carve-harness (11 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 302 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 2026-08-30.

Related

Other agents, from other repositories