What parable runs automatically, and when. A hook is a command Claude Code fires at a fixed moment, without you asking for it.
Where it lives
#!/bin/bash
# Periodic rule refresh: emits a short reminder at most once per 300s per
# session; silent otherwise. Wired to PostToolUse so long-running agents
# (subagents included) get the rules re-planted mid-run instead of only at
# session start.
inp=$(cat)
sid=$(printf '%s' "$inp" | sed -n 's/.*"session_id" *: *"\([^"]*\)".*/\1/p')
[ -z "$sid" ] && sid="global"
f="${TMPDIR:-/tmp}/claude-rulecard-$sid"
now=$(date +%s)
last=$(cat "$f" 2>/dev/null || echo 0)
if [ $((now - last)) -gt 300 ]; then
echo "$now" > "$f"
printf '%s' '{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"RULE REFRESH (auto, periodic): conclusions in the channel, cognition in the thoughts file - visible text is verdict + next step only, a few lines max; no wait/actually/maybe, no narrated deliberation. Directors: report each [DONE Pn] the moment it lands. Before declaring done, VERIFY with commands and paste the artifact (never claim): the build check AND a real runtime run, probe/test evidence for every behavior, docs regenerated, any standing logs appended."}}'
fi
exit 0
Read the script before you install anything that runs on your machine. This is the one part of a plugin that acts without being asked.
**Parable is an unofficial, community-made pseudo-Fable mode for Claude Opus (and Sonnet): Claude Fable 5's working discipline, distilled into a Claude Code skill set plus a hook mechanism.** It is not affiliated with or endorsed by Anthropic, and everything
Stars on GitHub
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraA Claude Code plugin with skills for auditing a whole repo, reviewing a change, listing deferred shortcut comments, and showing measured savings and a quick command reference.
@dietrichgebertWalks a software change from a written spec through design, testing, code review, CI/CD, and release, applying the matching engineering skill at each stage. Useful for developers using Claude Code on full development workflows.
@addyosmaniPersistent file-based planning for AI coding agents on long-running, multi-step tasks. It keeps task_plan.md, findings.md and progress.md on disk, so work can resume after /clear or context compaction.
@othmanadiA spec-driven development workflow for Claude Code that guides a project through planning, phases, milestone audits and fixes. Includes skills to generate tests from UAT criteria and to audit completed work.
@open-gsdChinese-language skill pack for Claude Code that adds workflow guidance for brainstorming, TDD, debugging, and code review, plus Chinese conventions for commits, documentation, and domestic Git platforms like Gitee and Coding.net.
@jnmetacodeGives Claude Code semantic search, dependency graph and architecture context over a codebase, so an AI assistant can explore and understand a project's code. Includes skills for indexing a project and managing its file watching.
@giancarloerraA lightweight code search engine that uses AST-based semantic search with local embeddings and incremental indexing. It helps Claude Code users find code faster and more efficiently.
@cocoindex-io