realgarit

12 mods across 1 repository, 22 stars between them.

fable-baton

01

realgarit/fable-baton

Plugin Claude Code

Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents.

22 29d ago A tokens not measured original MIT

fable-baton

02

realgarit/fable-baton

Plugin Claude Code

Turns Fable 5 into a token-frugal orchestrator: Fable keeps judgment, tiered Opus/Sonnet/Haiku agents do the labor.

22 29d ago A tokens not measured original MIT

realgarit/fable-baton

Instructions file CodexOpenCode

Instructions for realgarit/fable-baton, covering fable-baton: agent instructions, project memory (distilled), cross-agent conventions and working notes.

22 29d ago C 1,822 tokens original MIT

realgarit/fable-baton

Instructions file

Instructions for realgarit/fable-baton, a project described as: Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents.

22 29d ago C 36 tokens original MIT

architect

05

realgarit/fable-baton

Agent

Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.

22 29d ago A 54 tokens original MIT

executor

06

realgarit/fable-baton

Agent

Standard engineering execution. Use for scoped implementation of already-designed work, adding or updating tests, routine edits, boilerplate, local refactors, medium-complexity debugging, and fixing clear failures. Does not make product calls or change architecture.

22 29d ago A 50 tokens original MIT

scout

07

realgarit/fable-baton

Agent

Cheap evidence gathering. Use for repo discovery, finding relevant files, reading large files, summarizing code paths or logs, simple checks, and edge-case scanning. Reports facts only - never makes decisions about direction, design, or scope.

22 29d ago A 50 tokens original MIT

verifier

08

realgarit/fable-baton

Agent

Independent evidence-based verification. Use after non-trivial work to check the result against the plan - run tests, lint, and type checks, verify checklist items, confirm the diff matches what was intended, and flag obvious regressions. Reports pass/fail with evidence; never fixes anything.

22 29d ago A 60 tokens original MIT

SessionStart

09

realgarit/fable-baton

Hook

Runs when a session starts, executing session-start.sh. From realgarit/fable-baton.

22 29d ago A tokens not measured copy · 63% MIT

UserPromptSubmit

10

realgarit/fable-baton

Hook

Runs when you submit a prompt, before the agent sees it, executing prompt-nudge.sh. From realgarit/fable-baton.

22 29d ago A tokens not measured copy · 100% MIT

PostToolUse

11

realgarit/fable-baton

Hook

Runs after a tool call finishes, executing inline-counter.sh. From realgarit/fable-baton.

22 29d ago A tokens not measured copy · 56% MIT

baton-setup

12

realgarit/fable-baton

Skill Claude CodeCodex

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/settings.json and verifies the plugin is fully installed.

22 29d ago B 69 tokens original MIT