judgemind

26 mods across 1 repository, 2 stars between them.

PreToolUse

01

judgemind/judgemind

Hook Claude Code

Runs before the agent uses a tool for Bash, Edit, Write and Agent tool calls, executing preflight-bash.sh, dispatcher-guard.sh, worktree-write-guard.sh and agent-worktree-guard.sh via bash (4 commands). From judgemind/judgemind.

2 1mo ago A tokens not measured

PostToolUse

02

judgemind/judgemind

Hook Claude Code

Runs after a tool call finishes for Agent tool calls, executing check-inbox.sh and agent-cwd-guard.sh via bash (2 commands). From judgemind/judgemind.

2 1mo ago A tokens not measured

SessionStart

03

judgemind/judgemind

Hook Claude Code

Runs when a session starts, executing session-start.sh via bash. From judgemind/judgemind.

2 1mo ago A tokens not measured

SessionEnd

04

judgemind/judgemind

Hook Claude Code

Runs when a session ends, executing session-end.sh via bash. From judgemind/judgemind.

2 1mo ago A tokens not measured

judgemind

05

judgemind/judgemind

Settings file Claude Code

Agent settings declaring 4 hook events (PreToolUse, PostToolUse, SessionStart, SessionEnd) and 93 allowed tools.

2 1mo ago C tokens not measured

judgemind/judgemind

Skill Claude CodeCodex

Weekly LLM carry-forward audit across CA counties — runs scripts/auditllmcarryforward.py, applies per-axis thresholds, files agent/ready follow-ups for trips, and posts a heartbeat comment on the long-lived audit-log issue. Triggered by the daemon scheduler weekly.

2 1mo ago A 56 tokens

audit

07

judgemind/judgemind

Skill Claude CodeCodex

Periodic codebase health audit — reviews recent PRs, checks for dead code, test gaps, performance issues, security concerns, dependency health, and CI pipeline health. Files issues for findings. Triggered by the dispatcher every 20 merged PRs.

2 1mo ago A 50 tokens

diagnose-failure

08

judgemind/judgemind

Skill Claude CodeCodex

Diagnose a dispatcher-v3 task-runner failure. Reads the agent's session transcript from S3 (compact), falling back to raw jsonl or CloudWatch Logs. Takes side effects directly with full peer-agent authority — close issue, file follow-up, comment, edit labels, or re-add agent/ready to retry. Writes…

2 1mo ago A 77 tokens

dispatcher-audit

09

judgemind/judgemind

Skill Claude CodeCodex

Periodic dispatcher operational-health probes — runs convergence-regression, bad-outcome-streak, and site-health checks and files GitHub issues for any findings. Triggered by the daemon scheduler every 6 hours.

2 1mo ago A 41 tokens

judgemind/judgemind

Skill Claude CodeCodex

Daily dispatcher failure-summary report — queries last-24h aggregations from dispatcher., renders phone-readable markdown, and auto-PRs to docs/dispatcher-daily/YYYY-MM-DD.md. Triggered by the daemon scheduler at 12:00 UTC.

2 1mo ago A 50 tokens

dispatcher-startup

11

judgemind/judgemind

Skill Claude CodeCodex

Dispatcher startup subagent — runs the heavy one-shot startup queries (stale-worktree sweep, stale-assignment cleanup, agent/ready queue scan, trust-check, orphan-PR triage) in an isolated subagent context and returns a compact markdown summary. Keeps the dispatcher's main context clear of 100k tokens of raw GitHub…

2 1mo ago A 72 tokens

dispatcher

12

judgemind/judgemind

Skill Claude CodeCodex

Opt-in autonomous work queue manager — launches /task agents, merges PRs, triages issues, and communicates via Telegram. Usage: /dispatcher (default 5 slots), /dispatcher 3 (custom slot count), /dispatcher #589 #590 (specific issues only).

2 1mo ago C 0 tokens

file-issue

13

judgemind/judgemind

Skill Claude CodeCodex

File a GitHub issue in judgemind/judgemind with the repo's house conventions locked in — conventional-commits title, body written to a temp file, Verify lines on every acceptance criterion, proper labels, and correct blocking dependencies. Thin guardrail — the full authoring reference lives in…

2 1mo ago A 70 tokens

ralph

14

judgemind/judgemind

Skill Claude CodeCodex

Ralph loop — iterative work-review cycle with fresh context each iteration. Spawns a worker subagent to implement, then runs up to three reviewers sequentially (Gemini standard, Gemini adversarial, Claude). Loops until all required reviewers agree to SHIP or max iterations reached. Called by /task for implementation…

2 1mo ago A 65 tokens

screenshot

15

judgemind/judgemind

Skill Claude CodeCodex

Take a screenshot of a page on dev.judgemind.org for visual iteration. Use when working on frontend tasks to see what the page looks like, verify layout changes, or debug UI issues.

2 1mo ago A 40 tokens

spotcheck

16

judgemind/judgemind

Skill Claude CodeCodex

Periodic data quality spot-check — a senior engineer doing a high-level review for problems a human reviewer would notice. Discovers, root-causes, and (when scoped) fixes inline.

2 1mo ago A 37 tokens

task-v2-fix-ci

17

judgemind/judgemind

Skill Claude CodeCodex

Fix-CI phase for the per-phase /task-v2 pipeline. Reads CI failure logs and the PR diff, produces a patch commit OR an explicit blocker signal.

2 1mo ago A 33 tokens

judgemind/judgemind

Skill Claude CodeCodex

Fix-conflict phase for the per-phase /task-v2 pipeline. Reads a rebase-conflict bundle, resolves conflicts semantically against updated origin/main content, and produces either a resolved-file set OR an unresolvable signal.

2 1mo ago A 46 tokens

task-v2-operational

19

judgemind/judgemind

Skill Claude CodeCodex

Operational handler for the per-phase /task-v2 pipeline. Executes non-coding tasks (script runs, DB queries, gh actions, data rebuilds) without creating a PR. Emits a structured verdict for the dispatcher to advance the agent pipeline.

2 1mo ago A 49 tokens

task-v2-plan

20

judgemind/judgemind

Skill Claude CodeCodex

Plan phase for the per-phase /task-v2 pipeline. Reads an issue + comments, produces a plan document, scope-check findings, and a go/no-go signal. Called once per task by the dispatcher daemon before /task-v2-ralph.

2 1mo ago A 51 tokens

task-v2-ralph

21

judgemind/judgemind

Skill Claude CodeCodex

Ralph phase for the per-phase /task-v2 pipeline. Iterative worker + reviewer loop, returns SHIP verdict plus a committed implementation diff on the worktree branch. Long-tail phase (45-90 min internally).

2 1mo ago A 45 tokens

task-v2-retro

22

judgemind/judgemind

Skill Claude CodeCodex

Retrospective phase for the per-phase /task-v2 pipeline. Reads the full agent history (phasetransitions, failures, PR URL), produces zero-to-many retro issue bodies for the daemon to file.

2 1mo ago A 42 tokens

task-v2-summary

23

judgemind/judgemind

Skill Claude CodeCodex

Summary phase for the per-phase /task-v2 pipeline. Reads the issue body and the git diff, produces a process-summary issue comment (with AC mapping), a conventional commit message, a PR title, and a PR body.

2 1mo ago A 46 tokens

task-v2-verify

24

judgemind/judgemind

Skill Claude CodeCodex

Verify phase for the per-phase /task-v2 pipeline. Reads the merged PR plus deploy status plus acceptance criteria, produces a verification-evidence comment with per-criterion proof against dev.

2 1mo ago A 37 tokens