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.
npx agentmods add skills/realgarit/fable-baton/baton-setupnpx skills add realgarit/fable-baton --skill baton-setupgit clone --depth 1 https://github.com/realgarit/fable-batonWrote 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.
[](https://agentmods.dev/skills/realgarit/fable-baton/baton-setup)<a href="https://agentmods.dev/skills/realgarit/fable-baton/baton-setup"><img src="https://agentmods.dev/badge/skills/realgarit/fable-baton/baton-setup.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00069 | $0.00696 |
| Opus 5 | $0.00034 | $0.00348 |
| Sonnet 5 | $0.00014 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade B, and why
baton-setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
description: One-time setup and health check for fable-baton. Use when the user asks to set up, configure, verify, or troubleshoot fable-baton - sets the default model to "best" (Fable 5 with Opus fallback) in ~/.claude/ How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
baton-setup
One-time setup for fable-baton. Run each step in order. Never rewrite ~/.claude/settings.json wholesale - edit only the named keys and preserve everything else.
Step 1 - Read current state
- Read
~/.claude/settings.json(if missing, you will create a minimal one). - Check
echo "$CLAUDE_CODE_SUBAGENT_MODEL". If set, warn the user: this variable silently overrides every agent'smodelfrontmatter and defeats the tiering. Recommend unsetting it, but do not unset it yourself without approval.
Step 2 - Propose changes and get approval
Show the user exactly what you will change before writing anything:
| Key | Rule |
|---|---|
model |
If absent → set "best". If present with a different value → ask: keep theirs, or switch to "best"? (best resolves to Fable 5 when the account has access, otherwise the latest Opus.) If already "best" → no change. |
fallbackModel |
If absent → add ["opus", "sonnet"] (covers overload/unavailability). If present → leave it. |
availableModels |
Only if the key already exists (it is an allowlist): ensure it contains "opus", "sonnet", "haiku", and the chosen main-model value. If absent → do not add it. |
Back up the file first: copy it to ~/.claude/settings.json.baton-backup-<YYYYMMDD-HHMMSS> (skip if the file didn't exist).
Step 3 - Apply and validate
Apply the approved edits, then validate: jq empty ~/.claude/settings.json must exit 0 (or parse the JSON yourself if jq is unavailable).
If Claude Code rejects the best alias at startup (older versions), fall back to "opus" and suggest updating Claude Code.
Step 4 - Verify the install
- Confirm the four agents are available: scout, executor, architect, verifier (ask "which subagent types are available?" or check the Agent tool's list).
- Confirm the orchestration policy is present in context (it is injected at session start; in a session started before install it won't be - that's expected).
- Tell the user to restart their Claude Code session: agents and the model setting load at session start.
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.
- 4d ago First seen · 47 lines · 69 tokens per session scan B cb2d1af85cfd
baton-setup is a skill published in the GitHub repository realgarit/fable-baton (24 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 696 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
goal
Run a large or unfamiliar goal through the full ballast pipeline — mobilize what you already hold, terrain scan, full skeleton, atomic foundation learning with verification, then build from bedrock to a verified done. Use when the user hands over a big goal, enters a new field, or asks to learn X in order to achieve Y.
brain-init
Scaffold a file-based memory system (index, decision ledger, open questions, session log, optional product truth file) so a project can serve as a durable second brain. Use when the user wants to set up memory, an external brain, or the ballast structure in a project.
proof-standard
Never make an external-facing claim about a product without evidence from a truth file. Use when writing marketing copy, announcements, docs, landing pages, investor material, or answering "can our product do X".
rehearsal
Test a deliverable on a zero-context reader before it ships. Use before shipping any document, guide, kit, or handoff meant to work without you, and before calling a deliverable done in goal Phase 5.
report
Read the delivery log and say which rules actually fire, which never have, and what to prune or fix. Use when the user asks whether ballast is doing anything, wants to clean up their rule catalog, or on a periodic review.
persona-safety
페르소나 v5 안전 작업 — 보안 always-on·비가역 작업 게이트·코드 메타규칙·모바일 UI(375px) 검증·외부도구 도입검토. 코드/UI/보안/배포/삭제/force push 작업 시 로드.