Agent
README: "The disallowedtools field is respected when determining write capability — an agent with tools: write + disallowedtools: write correctly gets read-only memory.".
57 tagged pi extension, measured the same way as everything else here.
Browse within: pi 32subagents 26pi-package 25pi-coding-agent 19agent-management 17agent-manager 17coding-agent 6
Agent
README: "The disallowedtools field is respected when determining write capability — an agent with tools: write + disallowedtools: write correctly gets read-only memory.".
Agent
A read-only memory agent. Per the README, agents without write/edit tools auto-get a read-only memory fallback: existing memory is injected, no write access is granted, and no memory directory is created (so project scope is safe here — nothing is written into the repo).
Agent
A write-capable memory agent. Per the README, agents with write/edit tools get full read-write memory; the memory tool set is completed (edit is auto-added) and a writable memory block is injected into the system prompt. Scope user so the memory dir is created under the hermetic HOME, never in the repo.
Agent
Answer questions about a Codex session JSONL by rendering it with session-view and inspecting the rendered transcript.
Agent
Ask questions about a Pi session JSONL file (rehydration / forensics).
Agent
Production readiness review: quality, security, testing (read-only).
Agent
Implement tasks via TDD and commit small changes.
Agent
General-purpose worker for isolated tasks.
Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
Agent Claude Code
Planning specialist that explores requirements and code context, weighs architecture trade-offs, and produces ordered implementation plans or plan files. May write planning artifacts; does not edit production code.
Agent Claude Code
Broad correctness and regression reviewer for behavior breakage, boundary/edge-case predicates, API/CLI/devex regressions, feature-gate leaks, migrations, state semantics, and cross-module side effects.
Agent Claude Code
Documentation accuracy reviewer. Verifies changed doc claims against implementation, re-derives transcribed values, checks citations resolve, audits drift.
Agent
Queries and explores Solana blockchain accounts, displaying balances, token holdings, and transaction history in user-friendly format. Triggered when users ask about account balances, token holdings, or account details for specific addresses. Automatically fetches from blockchain and presents data clearly. Enforces…
Agent
Analyzes Solana blockchain transactions and explains them in simple, non-technical language. Triggered when users ask about transactions, provide transaction hashes, or request transaction analysis. Automatically fetches transaction details and breaks down complex operations into understandable explanations. Enforces…
Agent
The Claude Code plugin adds /resume-from and includes the matching command binary.
Agent
The Codex plugin adds a /resume-from prompt. The prompt runs the matching published command package.
Agent
Pi supplies the native session picker and can open the imported session without a restart.