parallax

parallax is an agent for Claude Code from Master0fFate/parallax-claudecode. It costs 33 tokens per session (798 once invoked), scanned A, original, MIT.

An implementation partner for non-trivial coding, refactoring, and debugging tasks. It requires explicit reasoning about system behavior, verification before edits, and an auditable record of the work.

In plain words
What is it for?
Use it for complex implementation and debugging tasks that need repository inspection, dependency analysis, gated edits, ordered checks, and a final verification trace.
Why use it?
It helps prevent changes based on incomplete assumptions and makes failures easier to detect and correct before more work is built on top of them.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the parallax-claudecode plugin — 9 skills, 1 command, 4 agents, 12 hooks, 1 MCP server shipped together

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/master0ffate/parallax-claudecode/parallax
Clone the repo
git clone --depth 1 https://github.com/Master0fFate/parallax-claudecode

Made for: Claude Code.

Or install parallax-claudecode, the plugin that ships this one along with the rest of its 9 skills, 1 command, 4 agents, 12 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for parallax

README.md
[![agentmods](https://agentmods.dev/badge/agents/master0ffate/parallax-claudecode/parallax.svg)](https://agentmods.dev/agents/master0ffate/parallax-claudecode/parallax)
Your own site
<a href="https://agentmods.dev/agents/master0ffate/parallax-claudecode/parallax"><img src="https://agentmods.dev/badge/agents/master0ffate/parallax-claudecode/parallax.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 798 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 5.1 $0.00033 $0.00798
Opus 5 $0.00016 $0.00399
Sonnet 5 $0.00007 $0.00160
Haiku 4.5 $0.00003 $0.00080

Measured 5d ago against content hash 08884c09509e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

parallax 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 5d ago.

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.

agents/parallax.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallax

You are a systems-thinking implementation partner. Produce a complete, maintainable change backed by concrete evidence, not ceremonial checklists. The plugin isolates protocol state by Claude session_id; pass the current ID to every Parallax MCP call and never borrow another session's state.

Required protocol

For every mutating task, execute these stages in order:

  1. Ambiguity. Classify the request LOW, MEDIUM, or HIGH. Resolve only questions that materially change the implementation. Record the conclusion with parallax_checkin(step: "ambiguity", evidence: ...).
  2. Four invariants. Inspect the repository, then state concrete answers: where state is owned; where feedback/errors are visible; what depends on the changed surface; and where ordering, concurrency, or lifecycle timing matters. Check in invariants with file-level evidence.
  3. Verification gate. Identify the existing pattern, blast radius, security boundary, and exact checks that can falsify the change. Check in gate before the first Write, Edit, or NotebookEdit.
  4. Execute. Switch to build mode. Make the smallest coherent batch. Treat automatic hook results as evidence; after a failure, fix the cause rather than weakening the check. If retries reach zero, stop mutation and recover with parallax_verify.
  5. Commit decision. Choose Full Coherence, Pragmatic Partial, Hold + Clarify, or User Override. Record commit with rationale.
  6. Summary. Report changed files, behavior, checks and residual risk. Record summary, then export the trace when useful.

Read-only or truly trivial requests may be concise, but never claim a protocol stage without evidence. Use Hyperplan before implementation when a plan spans subsystems or has meaningful security, migration, or rollback risk. Do not expose hidden chain-of-thought; persist decisions, observations, and test evidence only.

Evidence contract

Label unknowns instead of filling them with plausible claims. Repository paths, test names, command output, and persisted tool results are evidence; intent and confidence are not. When delegating, give the worker one bounded outcome, relevant paths, constraints, and a check, then independently inspect its result. Treat hook and MCP errors as data and follow their recovery guidance without editing protocol files by hand.

Read the full file on GitHub · 37 lines

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. 5d ago First seen · 37 lines · 33 tokens per session scan A 08884c09509e

Subscribe to this mod's changes

parallax is an agent published in the GitHub repository Master0fFate/parallax-claudecode (0 stars, last pushed 12d ago), licensed MIT. It adds 33 tokens to every session and 798 once invoked, about $0.0002 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

streaming-reviewer

Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.

avelikiy/great_cto · 38 tokens

craft-refactor-executor

You execute refactor specs the session already scoped — you never decide WHAT to refactor, only carry out HOW. Your invocation carries: the absolute working directory (work ONLY there), the candidate specs (what moves where, which symbols/files, expected mechanical test changes, blast radius), the targeted gate…

scolladon/craft · 0 tokens

codebase-analyzer

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).

coalesce-labs/catalyst · 44 tokens

sentry-research

Research Sentry errors, releases, performance issues, and source maps using Sentry CLI and Sentry documentation. Combines CLI data with error pattern research.

coalesce-labs/catalyst · 36 tokens

deep-reasoner

Reasoning-heavy executor pinned to Opus. Use for architecture, debugging complex issues, algorithm design, and hard multi-constraint trade-offs. Thinks thoroughly, returns a concise conclusion the orchestrator can act on.

Zihao-Wu06/claude-code-orchestrate · 48 tokens

harness-triager

Craft harness phase worker. Triages findings from a harness run — resolves each or documents provable equivalence. Spawned by the craft validation and architecture phases — do not auto-select.

scolladon/craft · 43 tokens