kanevry
01Plugin Claude Code
Plugin marketplace listing 1 plugin: session-orchestrator.
49 3d ago A
tokens not measured
original MIT
Plugin Claude Code
Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.
49 3d ago A
tokens not measured
original MIT
SessionStart
03Hook Claude Code
Runs when a session starts on ., running an inline shell check. From Kanevry/session-orchestrator.
49 3d ago A
tokens not measured
original MIT
PostToolUse
04Hook Claude Code
Runs after a tool call finishes for Write, Edit, Write, Edit, Write and Edit tool calls, executing .test.ts with --write (3 commands). From Kanevry/session-orchestrator.
49 3d ago A
tokens not measured
original MIT
PreToolUse
05Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From Kanevry/session-orchestrator.
49 3d ago A
tokens not measured
original MIT
Notification
06Hook Claude Code
Runs when the agent sends a notification for . tool calls, running an inline shell check. From Kanevry/session-orchestrator.
49 3d ago A
tokens not measured
original MIT
Settings file Claude Code
Agent settings declaring 4 hook events (SessionStart, PostToolUse, PreToolUse, Notification) and 41 allowed tools.
49 3d ago C
tokens not measured
original MIT
Command Cursor
Multi-story autopilot orchestrator — runs N parallel issue pipelines in isolated git worktrees (v3.6 Phase D thin-slice).
49 3d ago A 28 tokens
original MIT
autopilot
09Command Cursor
Autonomous session-orchestration loop with kill-switches (Phase C-1.b — all 10 kill-switches shipped).
49 3d ago A 26 tokens
original MIT
bootstrap
10Command Cursor
Scaffold the minimum repo structure required by session-orchestrator.
49 3d ago A 12 tokens
original MIT
brainstorm
11Command Cursor
Run a lightweight Socratic design dialogue (3-5 AUQ rounds) and write a spec markdown file before any implementation work. Use BEFORE /plan feature when scope/UX is ambiguous.
49 3d ago A 39 tokens
original MIT
close
12Command Cursor
End session with verification, commits, and documentation.
49 3d ago A 9 tokens
original MIT
Command Cursor
Classify and apply a version bump to a machine-readable contract (JSON Schema, API spec, config schema) — version literals, consumer compatibility, changelog entry, downstream drift.
49 3d ago A 35 tokens
original MIT
debug
14Command Cursor
Run a 4-phase systematic debugging investigation before proposing any fix. Iron Law — NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Produces a .orchestrator/debug/ artifact the fixer agent must reference.
49 3d ago A 44 tokens
original MIT
discovery
15Command Cursor
Systematic quality discovery and issue detection.
49 3d ago A 7 tokens
original MIT
dispatcher
16Command Cursor
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
49 3d ago A 31 tokens
original MIT
eli5
17Command Cursor
Say the last answer again in plain words — same facts, in the order the operator needs them. Optional topic argument.
49 3d ago A 24 tokens
original MIT
eval
18Command Cursor
Run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed session against the pre-registered rubric-v1 dimensions.
49 3d ago A 38 tokens
original MIT
evolve
19Command Cursor
Extract session patterns into reusable learnings.
49 3d ago A 7 tokens
original MIT
go
20Command Cursor
Approve session plan and begin wave execution.
49 3d ago A 7 tokens
original MIT
grill
21Command Cursor
Stress-test a plan, design, or PRD before any build — relentless one-question-at-a-time interrogation that hunts contradictions against the code and challenges assumptions. Composable; no HARD-GATE.
49 3d ago A 39 tokens
original MIT
Command Cursor
Run the harness audit and report the rubric score for this repository.
49 3d ago A 12 tokens
original MIT
Command Cursor
Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
49 3d ago A 56 tokens
original MIT
Command Cursor
Manual memory consolidation — review, consolidate, and prune memory files (Dream-equivalent).
49 3d ago A 17 tokens
copy · 78% MIT