Plugins · keiseilab/keiseikit

keisei

Constructor-Pattern agent substrate for Claude Code: agent manifests, portable skills, hooks, Rust workspace primitives (installable via MANIFEST.toml profiles through classic ./install.sh), typed artifact handoff, sleep-sync cloud consolidation, MCP server layer.

CLEARED_STATICagent-agnosticv0.38.0

Pipeline results

Coverage

CLEARED_STATIC

Tests run

7 / 8

Portability

Agent-agnostic (works beyond Claude)

Type

Plugins

Tests & results

What the pipeline checked

TestStateResult or reason

eligibilityranall eligibility checks passed

dedupranunique -- no near-duplicate found

clocran203190 code lines / 2352 files

secretsran0 PLAUSIBLY-LIVE / 1 FLAG-INFO

egressran3 lexical match(es) — FLAG-INFO (C-01: semantic analysis deferred to v2)

injectionranno patterns matched (confidence: STANDARD)

required-fieldsranrequired fields present: name, version, description

behaviouraldeferredbehavioural assessment deferred (v1): 15 JS/TS entry point(s); Python with non-stdlib imports (committed-only policy): [('_primitives/_rust/kei-cortex/scripts/whisper_worker.py', 'faster_whisper'), ('_primitives/_rust/kei-cortex/scripts/whisper_worker.py', '__future__')]

What's inside

Components found

_generated/architect.md

componentmedium

_generated/code-implementer-flutter.md

componentmedium

_generated/code-implementer-go.md

componentmedium

_generated/code-implementer-python.md

componentmedium

_generated/code-implementer-rust.md

componentmedium

_generated/code-implementer-swift.md

componentmedium

_generated/code-implementer-typescript.md

componentmedium

_generated/code-implementer.md

componentmedium

_generated/cost-guardian.md

componentmedium

_generated/critic-anti-pattern.md

componentmedium

_generated/critic-bug.md

componentmedium

_generated/critic-perf.md

componentmedium

_generated/critic-tech-debt.md

componentmedium

_generated/critic.md

componentmedium

_generated/fal-ai-runner.md

componentmedium

_generated/infra-implementer-cicd.md

componentmedium

_generated/infra-implementer-container.md

componentmedium

_generated/infra-implementer-iac.md

componentmedium

_generated/infra-implementer-secrets.md

componentmedium

_generated/infra-implementer.md

componentmedium

Coverage

Not assessed

behavioural execution not run
egress patterns logged (FLAG-INFO): 3 lexical match(es)
secret pattern(s) classified FLAG-INFO: 1 match(es)

README

From the repository

# KeiSeiKit

A **multi-LLM substrate** for agentic coding. Same agent definition,
any LLM backend — Claude Code, Grok, Antigravity (Gemini), GitHub
Copilot, or Kimi. Pick your orchestrator with `kei pick`; agents
spawn sub-agents on other LLMs via MCP `spawn_agent`; safety hooks
enforce on every backend through a 3-tier model. Three-phase nightly
sleep consolidates 30-session windows into morning markdown reports.

**Apache 2.0** — explicit patent grant + retaliation clause.

## Highlights

- **5 LLM CLIs unified.** Claude Code (native hooks), Grok (port to
  `~/.grok/settings.json`), Antigravity/Gemini, GitHub Copilot, Kimi.
  DNA-routed: each agent's manifest declares a `provider`;
  `kei agent ` resolves DNA → primary → claude fallback.
- **Sub-agents on any backend.** Agents call `spawn_agent` (built-in MCP
  tool in `kei-mcp`) to dispatch other agents to whichever LLM fits
  the task. Cross-CLI orchestration without lock-in — Grok can spawn
  critic@Claude, then ml-implementer@Gemini, all from one session.
- **3-tier policy enforcement.** Claude + Grok TIER 1 (full native
  PreToolUse), Copilot TIER 2 (MCP-wrapped + `--excluded-tools=shell`),
  Agy + Kimi TIER 3 (advisory). `n…

← Back to Plugins