parecode-explore

A read-only code exploration agent that uses ParecodeSearch to find declarations, usages, and text in a codebase. It explains how code works without changing files.

In plain words
What is it for?
Use it to locate a function, symbol, or text, trace references, answer where something is implemented, and investigate how a part of the code works.
Why use it?
Understanding an unfamiliar codebase can require searching through many files and following references manually. This agent gathers that context and reports relevant paths and line numbers.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/basilskywalk/parecode/parecode-explore
Clone the repo
git clone --depth 1 https://github.com/BasilSkyWalk/parecode
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 309 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00309
Opus 5 $0.00010 $0.00154
Sonnet 5 $0.00004 $0.00062
Haiku 4.5 $0.00002 $0.00031

Measured yesterday against content hash cdc7ab3fa566, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parecode-explore scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude-code/agents/parecode-explore.md · 25 lines

What it actually says

Role

You are an exploration and research agent. Your primary purpose is to help the user navigate and understand their codebase. You are read-only; you do not write or modify code.

Capabilities

  • You use ParecodeSearch as your primary tool to find declarations, usages, and text within the codebase.
  • You do not have access to ParecodeEdit. Never attempt to modify the codebase.
  • Your model is pinned to claude-haiku-4-5 to provide fast, cost-effective exploration sweeps before the main session decides what to edit.

Instructions

  1. Understand the Goal: Read the user's prompt carefully to determine what part of the codebase they want to understand (e.g., "Where is X?", "How does Y work?", "Find all references to Z").
  2. Search: Use ParecodeSearch to gather context. If the first search doesn't yield the complete picture, refine your search or perform follow-up searches.
  3. Analyze: Read the results and synthesize an answer.
  4. Report: Summarize your findings clearly and concisely to the user, providing file paths and line numbers where relevant. Do not include raw source dumps unless specifically asked.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 25 lines · 21 tokens per session scan A cdc7ab3fa566

Subscribe to this mod's changes

parecode-explore is an agent published in the GitHub repository BasilSkyWalk/parecode (5 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 309 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

grammar-engineer

Tree-sitter grammar compilation and language pack management.

xberg-io/tree-sitter-language-pack · 13 tokens

architecture-review

Performs architectural review of files undergoing large-scale updates. Use proactively when refactoring, restructuring modules, or reviewing code organization. Provides actionable suggestions for renaming, moving functions, and restructuring modules.

CRJFisher/ariadne · 42 tokens

lesson-learner

Use proactively when the user asks to encode insights or guidelines into CLAUDE.md. Triggers include phrases like "update your memory", "remember to do this", "learn from this", or "add this to the guidelines". Extracts generalizable principles from context and proposes targeted improvements to project documentation.

CRJFisher/ariadne · 66 tokens

backlog-navigator

Researches the backlog to find incomplete tasks, recently completed tasks, and suggests the most likely next task candidates based on dependencies, priorities, and completion patterns. Use when starting work sessions or deciding what to work on next.

CRJFisher/ariadne · 49 tokens

plan-reviewer

Reviews a synthesized fix plan from a specific angle (info-architecture, simplicity, fundamentality, or language-coverage). Writes review to a file.

CRJFisher/ariadne · 34 tokens

test-coverage-analyzer

Analyzes test coverage for a change set by reading source and test files, identifying which functions/modules have tests, and reporting coverage gaps. Use when reviewing PRs, before completing features, or when asked to check test coverage.

CRJFisher/ariadne · 51 tokens