Dispute — Development skill for Claude Code
Contest a criterion on this session's receipt; the original stays next to the override and the receipt is re-scored.
How to install Dispute
Installs to ~/.claude/skills/kru3ish-tally-dispute/SKILL.md
mkdir -p ~/.claude/skills/kru3ish-tally-dispute && curl -fsSL https://raw.githubusercontent.com/kru3ish/tally/HEAD/commands/dispute.md -o ~/.claude/skills/kru3ish-tally-dispute/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Dispute does
description: Contest a criterion on this session's receipt; the original stays next to the override and the receipt is re-scored argument-hint: allowed-tools: Bash(node *)
node "${CLAUDE_PLUGIN_ROOT}/dist/cli.js" dispute --from-args "$ARGUMENTS" --plain
Report the re-scored receipt above to the user. The dispute is recorded with their reason and feeds Tally's calibration.
Alternatives in Development
- Internet Court Skill — The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 4.9k ★
- Pi Reserved Keybindings — Extensions cannot override these shortcuts — they are silently skipped by registerShortcut() 526 ★
- Fast Jev Compaction — Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scor 425 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Pick Stack
Confirm or override the default stack in CLAUDE.md. Only run if the default Next.js + Supabase stack is wrong
Axonflow Create Override
Create a governed AxonFlow session override with mandatory justification (TTL clamped server-side; critical-ri
Ldd Config
Show the current LDD hyperparameter config — which layer each value comes from (bundle default / project file
Ldd Set
Set a session-level LDD hyperparameter override. Syntax — /ldd-set key=value. Non-persisted; clears on session
Pair Verify
Use after you fix a bug and before you claim it fixed — it spawns ONE skeptic sibling session via CCC that mus
Cc Cache Keepalive
Keep the most recently used Claude Code prompt cache warm without polluting the original session.
Related Agents
Judge Panel
Use when a draft or a past winning entry must be scored against a contest's official rubric before submission.
Model Corroborator
Stage 5.5 of /analyze-policy. When the original reform has no exact-shape external comparator, runs the closes
Playwright Test Manager
QA test manager and senior authority for this suite. Owns strategy, scope, coverage gaps, and quality gates. U