A setup command for enabling fablize's always-on instructions in a project's or user's CLAUDE.md file.

It helps set up fablize locally for one project or globally for all projects, record progress, and optionally ask whether to star the repository.

It provides a controlled way to add the operating instructions while keeping a backup and allowing the setup to be cancelled.

setup — Command by fivetaku

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 commands/fivetaku/fablize/setup

Clone the repo

git clone --depth 1 https://github.com/fivetaku/fablize

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 482 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.

Model	Per session	Once invoked
Fable 5	$0.00018	$0.00482
Opus 5	$0.00009	$0.00241
Sonnet 5	$0.00004	$0.00096
Haiku 4.5	$0.00002	$0.00048

Measured yesterday against content hash 2030bfa84a6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

commands/setup.md · 42 lines

What it actually says

Run the fablize setup. Ask only once, up front.

Step 1 — Ask whether/where to set up (one question)

Use AskUserQuestion. Phrase the question and options in the user's current conversation language (detect it from recent messages).

Question (meaning, translate to the user's language): "Set up fablize?"
Options (meaning, translate):
1. "Local — this project only (recommended)"
2. "Global — all projects"
3. "Cancel"

If the user picks "Cancel", stop and do nothing.

Step 2 — Run setup

For "Local" or "Global", run setup:

bash ${CLAUDE_PLUGIN_ROOT}/setup/setup.sh <local|global>

setup.sh backs up CLAUDE.md, injects the  block, and writes ~/.fablize/progress.json. It never stars the repo by itself. Report the result briefly.

Step 3 — GitHub star (opt-in, asked at most once)

Run:

bash ${CLAUDE_PLUGIN_ROOT}/setup/setup.sh ask

If the output starts with STAR_ASK, immediately call the AskUserQuestion tool once, with the question and options phrased in the user's language (prefer the live conversation's language if it is evident; otherwise fall back to the language code after STAR_ASK — ko→Korean, ja→Japanese, en→English. Never default to one language blindly):

header: a short localized "GitHub Star" label
question: ask whether they'd like to give fablize a GitHub ⭐ to support it — note it is optional and every feature works either way
options: exactly two — (1) yes, star it → then run bash ${CLAUDE_PLUGIN_ROOT}/setup/setup.sh star yes; (2) no thanks → then run bash ${CLAUDE_PLUGIN_ROOT}/setup/setup.sh star no

If the output is empty, continue silently — the question was already asked before. Do not narrate beyond the question itself.

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.

yesterday First seen · 42 lines · 18 tokens per session scan A 2030bfa84a6e

Subscribe to this mod's changes

setup is a command published in the GitHub repository fivetaku/fablize (894 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 482 once invoked, about $0.0001 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.

agentic anthropic claude claude-code fable harness

setup

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Step 1 — Ask whether/where to set up (one question)

Step 2 — Run setup

Step 3 — GitHub star (opt-in, asked at most once)

What this file has done since we first saw it

Other commands, from other repositories

MIGRATE_DESIGN

proposal

plan

diff-script

toh-help

doctor