KonghaYao/peri

Adaptive Devflow helps choose a lightweight-to-heavy development workflow for issues, bugfixes, features, and refactors. It guides when to use coordination, review, and verification phases based on task risk and complexity.

Advisor Consultation uses a tool-free Opus second opinion to evaluate high-risk design trade-offs, unresolved failures, and cross-boundary decisions. Use it after gathering repository evidence when the main agent needs a careful review.

Auto Converge refines rules, prompts, and SKILL.md files until agents can follow them reliably. It uses external references and adversarial review loops when a spec is written but not being obeyed.

Auto Issue Fixer manages an issue from creation through fix, verification, and archival. Use it when someone describes a bug, asks to record a problem, fix an issue, verify a change, or archive a resolved issue.

Blog Writer provides a style guide for writing Peri project blog posts. Use it when drafting project intros, technical retrospectives, architecture discussions, or performance writeups in the Peri voice.

Codebase Index maps user intents like changing a threshold, tracing an event chain, or finding an entry point to the exact files and functions to open. It is used to quickly locate or rebuild per-crate code indexes for a Rust codebase.

Goal Mode tracks a single long-running objective across multiple turns. Use it for complex tasks that need continuous progress until completion, blocking, or reset.

Heavy Verify Loop runs a user-level verify, fix, and review cycle against the real Peri TUI using tmux, logs, and E2E helpers. Use it when a feature must be exercised like a real user until fresh end-to-end evidence shows no blocking problems.

LLM Log Analyzer analyzes LLM gateway request and response logs under ./data/. Use it to inspect sessions, compare requests, check token usage, and diagnose cache behavior or failures.

Langfuse interacts with Langfuse data through the CLI and helps retrieve documentation, concepts, and SDK guidance. Use it to query traces, prompts, datasets, scores, sessions, and other API resources or to understand Langfuse features.

Learn From History audits recent conversation history to find repeated failures, successful patterns, stable rules, and skill improvements. Use it when you need to summarize prior agent behavior or learn from recent runs.

Programmatic Tool Calling discovers extra tools and uses ESM code to compose dependent calls into one bounded run. Use it to filter, join, or summarize structured tool results without returning large intermediates.

Project Maturity Scanner scans a repository across tests, code quality, CI/CD, docs, security, and activity to produce a structured maturity report. Use it when evaluating a new codebase, reviewing release readiness, or doing a technical due diligence check.

SSH CLI runs commands and manages files on remote machines through the system ssh binary. Use it to diagnose connectivity, read or edit files, and transfer data on a server or dev box.

Scheduled Tasks lets you register recurring jobs with cron expressions and list or remove existing schedules. Use it for reminders, periodic reports, polling, or other tasks that should run on a fixed interval.

Skill Discovery helps a TUI detect newly created Claude Code skills and show them in the available skill list. Use it when a skill exists on disk but does not appear after refresh.

Ultra ADLC turns one large natural-language goal into a complete, audited delivery with independent verification. Use it for explicitly requested full deliveries that need end-to-end implementation and proof, not small fixes or ad hoc work.

Ultra Task supervises non-trivial work by delegating bounded investigation, implementation, testing, and review to subagents while the main agent coordinates scope, approvals, and verification. Use it when a task needs orchestration rather than a single direct step.

Ultracode orchestrates multiple agents in parallel or phased pipelines for complex tasks. Use it when work can be split into independent subtasks or when you need to coordinate several approaches at once.

Use Artifacts teaches when to publish work as a shareable HTML or Markdown artifact, and how to update it as a task progresses. It also covers the deferred tool flow for creating and revising artifacts.