orenluxy

orenluxy/fable-method

Plugin Claude Code

Plugin marketplace listing 1 plugin: fable-method.

orenluxy/fable-method

Plugin Claude Code

The Fable Method: systematic unknowns-discovery workflow based on Thariq's 'A Field Guide to Fable'. Blindspot scanning, structured interviews, prototype-first, implementation notes with deviation tracking, and merge quiz gates.

orenluxy/fable-method

Agent

Drafting agent for the merge-quiz skill. Collects the change inventory (git diff, file list, test status) and drafts the change report skeleton. Delegating this mechanical work to a cheaper model saves main-context tokens; the main model reviews and writes the quiz itself.

orenluxy/fable-method

Agent

Read-only exploration agent for the blindspot-pass and merge-quiz skills. Scans codebase structure, conventions, existing patterns, configs, and tests, and collects raw findings. Use whenever a fable-method skill needs territory scanning — delegating this to a cheap model saves main-context tokens.

orenluxy/fable-method

Hook

Runs when a session starts, executing session-start.sh via bash. From orenluxy/fable-method.

orenluxy/fable-method

Hook

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing posttool-guard.sh via bash. From orenluxy/fable-method.

orenluxy/fable-method

Hook

Runs when the agent finishes a response, executing check-notes.sh via bash. From orenluxy/fable-method.

orenluxy/fable-method

Skill Claude CodeCodex

Run a blindspot scan to surface the user's unknown unknowns BEFORE implementing a task. Use this whenever the user starts a non-trivial task in a domain they say (or appear) to be unfamiliar with, whenever they say "blindspot", "unknowns", "what am I missing", "before we start", or when a request is vague enough that…

orenluxy/fable-method

Skill Claude CodeCodex

Stop-loss discipline for implementation sessions - detect fix-loops and runaway token burn, and stop to replan instead of patching. Consult during any debugging or implementation session, especially when tests keep failing, the same file keeps being edited, or the user mentions stoploss, token budget, fix loops, or…

orenluxy/fable-method

Skill Claude CodeCodex

The routing logic of the Fable Method - decides which unknowns-discovery technique (blindspot-pass, interview-me, prototype-first, implementation-notes, merge-quiz) applies to the current task, and which to skip. Consult this at the START of any non-trivial task, or when the user says "fable", "the method", "how…

orenluxy/fable-method

Skill Claude CodeCodex

Maintain an IMPLEMENTATIONNOTES.md decision log during any multi-step implementation session. Use this in EVERY session that involves writing or modifying code across more than one file, or any session expected to run longer than a few tool calls. Records decisions, deviations from plan, and open questions so nothing…

orenluxy/fable-method

Skill Claude CodeCodex

Interview the user one question at a time to resolve ambiguities before or during implementation. Use whenever the user says "interview me", "ask me questions", "make sure you understand", or before starting any task where multiple ambiguous decisions would otherwise be guessed silently. Also invocable as…

orenluxy/fable-method

Skill Claude CodeCodex

Before merging or deploying the output of a long session, generate a change report with a comprehension quiz the user must pass. Use whenever the user says "merge", "deploy", "we're done", "wrap up", or at the end of any session that modified more than 150 lines or touched production-relevant code. Also invocable as…

orenluxy/fable-method

Skill Claude CodeCodex

Route each step of a workflow to the cheapest model that can do it well, using subagents with explicit model assignments. Consult whenever planning multi-step work, whenever the user mentions saving tokens/cost, choosing models, or "model economy", and whenever a fable-method skill involves scanning, drafting, or bulk…

orenluxy/fable-method

Skill Claude CodeCodex

For visual, design, or "I'll know it when I see it" tasks, generate cheap throwaway prototypes BEFORE touching real code. Use whenever the user asks for UI, dashboards, design directions, video/visual output, landing pages, or any task where their taste cannot be specified in words. Also invocable as /prototype-first .