Habit Judge — Development agent for Claude Code
Read-only verifier that scores a session, a diff, or a transcript against a habit set and returns an evidence-bound ledger.
How to install Habit Judge
Installs to ~/.claude/agents/agricidaniel-agentic-habits-habit-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/AgriciDaniel/agentic-habits/HEAD/agents/habit-judge.md -o ~/.claude/agents/agricidaniel-agentic-habits-habit-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Habit Judge does
name: habit-judge description: Read-only verifier that scores a session, a diff, or a transcript against a habit set and returns an evidence-bound ledger. Use for /habits check, for a completion gate that needs judgment rather than a shell test, and any time an adherence claim needs to come from something other than the context that produced the work. It cannot edit, so its verdict cannot be improved by fixing what it is judging. tools: Read, Grep, Glob
habit-judge
You judge whether
Alternatives in Development
- Kai Personal Assistant — Use this agent when the user mentions personal matters, health, habits, routines, personal organization, or an 523 ★
- Bug Verifier Agent — Expert in verifying bug fixes 85 ★
- Accounting Reviewer — Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterpri 83 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Skill Applied Judge
Use this agent at session-end Phase 3.6.6 (#645 L3) to judge — from the session transcript tail — whether each
Finding Verifier
Per-finding verification judge for the review pipeline — a FRESH context that receives exactly ONE candidate r
Output Auditor
The quality gate. Scores artifacts against a published rubric, verifies every citation against the ledger, and
Thales Judge
Thales convergence verdict. Reads full ledger and returns structured status. Spawned every 3rd cycle (as the s
Completion Judge
Summarizer
Draft a session-handoff summary so a fresh agent can continue with zero conversation context. Locates the curr
Related Skills
Hakim
A judgment layer for AI coding agents: smaller safe changes, native host integrations, and evidence-bound comp
Codemesh
Query the code knowledge graph before reading code. One-call context assembly via codemesh_answer returns inli
Anti Sloppifier
Audits a PM work session for AI slop, decision abdication, and thinking replacement. Run after strategy, specs