Jiusi-pys

Jiusi-pys/agent-plugins

Plugin Claude Code

Plugin marketplace listing 3 plugins: ohos-porting, auto-clean, multi-review.

Jiusi-pys/agent-plugins

Instructions file

Claude Code instructions for Jiusi-pys/agent-plugins, covering claude.md, project overview, repository structure, file format conventions and agent definitions (agents/.md).

Jiusi-pys/agent-plugins

Plugin Claude Code

Auto-cleans Claude Code tracking data and privacy information. Supports init reset, deep clean, and automatic cleanup on exit.

Jiusi-pys/agent-plugins

Command

Manual command. Performs a level 3 cleanup of sessions, history, session-env, and session-history.

Jiusi-pys/agent-plugins

Command

Manual command. Performs a level 5 full reset and ensures /.claude/settings.json contains the env disabling non-essential traffic.

Jiusi-pys/agent-plugins

Hook

Runs when the agent finishes a response, executing clean.sh and clear.sh (2 commands). From Jiusi-pys/agent-plugins.

Jiusi-pys/agent-plugins

Plugin Claude Code

A code-review pipeline that runs preliminary checks, sends code to specialised read-only checks, independently verifies findings, and makes a final decision.

Jiusi-pys/agent-plugins

Agent

Independent read-only architecture reviewer focused on long-term constraints beyond local code — module boundaries, duplication of capability, public-API/back-compat, migration expand/contract, rollout/rollback, and domain conventions. Use during parallel review of structural changes.

Jiusi-pys/agent-plugins

Agent

Independent read-only correctness reviewer. Use during parallel review of code changes to find broken invariants, bad state transitions, missing error propagation, races and edge cases introduced by the diff.

Jiusi-pys/agent-plugins

Agent

Independent read-only intent reviewer. Compares the diff against stated acceptance criteria and non-goals to find unmet requirements, violated non-goals, undeclared behavior, and missing required edge cases. Judges "is this what was asked", not "is this elegant". Use when an intent file or PR description exists.

Jiusi-pys/agent-plugins

Agent

Synthesizes verified verdicts, deterministic-gate state and risk tier into a single gate decision (PASS / PASSWITHNOTES / HUMANREQUIRED / BLOCK / REJECTINTAKE) plus a concise human report. Only verified findings may block. Use as the final step of the multi-review pipeline.

Jiusi-pys/agent-plugins

Agent

Cheap risk-tiering router for the multi-review pipeline. Reads REVIEW.md, scores the diff, assigns R0–R3, and selects the minimal sufficient sensor set. Use at the start of a code review to decide how much review fleet a change warrants.

Jiusi-pys/agent-plugins

Agent

Conditionally-triggered read-only runtime reviewer. Runs the narrowest safe targeted/repro commands to observe async timing, resource leaks, timeouts/retries, query counts and performance. Use for R2/behavioral changes where static reading is insufficient.

Jiusi-pys/agent-plugins

Agent

Independent read-only security reviewer organized around trust boundaries and data flow. Use during parallel review of changes touching auth, tenancy, injection surfaces, secrets/PII, dependencies, or user-controlled data reaching LLM prompts/tools.

Jiusi-pys/agent-plugins

Agent

Independent read-only test-integrity reviewer. Reads the test diff FIRST to catch deleted/skipped/loosened assertions, expectations rewritten to match wrong behavior, happy-path-only coverage, and implementation+test collusion. Use during parallel review of code changes.

Jiusi-pys/agent-plugins

Agent

Independently falsifies or verifies ONE candidate review finding from a clean context. Receives only the claim, location, target and reproduction hint — never the originating reviewer's reasoning. Use to confirm a candidate before it is allowed to block.

Jiusi-pys/agent-plugins

Command

A multi-stage code review process that sends different read-only checks to the parts of a change most likely to contain risk, then combines verified findings.

Jiusi-pys/agent-plugins

Skill Claude CodeCodex

Shared output contract for the multi-sensor code-review pipeline. Defines the Finding, Verifier verdict, Risk-route, and Judge gate schemas plus the evidence bar. Preloaded by every review subagent so candidate findings, verdicts and gate decisions share one machine-readable format.

Jiusi-pys/agent-plugins

Plugin Claude Code

A workflow for adapting Linux libraries or software to OpenHarmony, also known as OHOS or KaihongOS, an operating system platform. It covers analysis, cross-compilation, and deployment to a device.

Jiusi-pys/agent-plugins

Agent

A specialist agent for diagnosing failures when code is compiled for a different operating system or processor, especially OHOS.

Jiusi-pys/agent-plugins

Agent

An OHOS work scheduler for OpenHarmony and related systems such as KaihongOS. It analyzes requests and assigns them to a suitable OHOS specialist agent.

Jiusi-pys/agent-plugins

Agent

A feasibility-analysis agent for moving Linux software to OpenHarmony, an operating system for connected devices. It assesses the expected difficulty and risks of the port.

Jiusi-pys/agent-plugins

Agent

An architecture-planning agent for moving software from Linux to OpenHarmony, an operating system for connected devices. It plans code changes and ways to adapt Linux-specific interfaces to OpenHarmony interfaces.

Jiusi-pys/agent-plugins

Agent

An agent role for operating OHOS source code and builds on remote servers over SSH. OHOS is an operating system project.