horizon-auditor

horizon-auditor is an agent for Claude Code from Master0fFate/parallax-claudecode. It costs 32 tokens per session (339 once invoked), scanned A, original, MIT.

An independent reviewer for a completed Horizon worker attempt. It compares the requested acceptance criteria with repository evidence, tests, changed files, and an observed result receipt.

In plain words
What is it for?
Use it to decide whether a Horizon worker met every requirement, needs corrective work, or has remaining risk.
Why use it?
It reduces the risk of accepting work based only on the worker's explanation or incomplete evidence.

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

Good fit Use it to decide whether a Horizon worker met every requirement, needs corrective work, or has remaining risk.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/master0ffate/parallax-claudecode/horizon-auditor
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.

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 horizon-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/master0ffate/parallax-claudecode/horizon-auditor.svg)](https://agentmods.dev/agents/master0ffate/parallax-claudecode/horizon-auditor)
Your own site
<a href="https://agentmods.dev/agents/master0ffate/parallax-claudecode/horizon-auditor"><img src="https://agentmods.dev/badge/agents/master0ffate/parallax-claudecode/horizon-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 339 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00032 $0.00339
Opus 5 $0.00016 $0.00169
Sonnet 5 $0.00006 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 7d ago against content hash 1b96a51d6616, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

horizon-auditor 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 7d 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/horizon-auditor.md · 16 lines

What it actually says

Horizon Auditor

Audit exactly the assigned feature. You are distinct from its worker. Read the acceptance criteria, relevant diff/files, tests, and the already-observed schema-v2 receipt. Do not mutate files or state, run verification, delegate, or accept claims based only on worker prose.

Return accept only when every criterion is supported by repository evidence and the observed receipt verdict is pass; otherwise return corrective-worker. Your Markdown summary must be at most 2,000 characters and list criterion findings, evidence, verdict, and residual risk. The parent records the verdict; you cannot release the lock yourself.

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. 7d ago First seen · 16 lines · 32 tokens per session scan A 1b96a51d6616

Subscribe to this mod's changes

horizon-auditor is an agent published in the GitHub repository Master0fFate/parallax-claudecode (0 stars, last pushed 15d ago), licensed MIT. It adds 32 tokens to every session and 339 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

doc-sync-scan

Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning stale-doc candidates for the…

RockyHong/super-bootstrap · 0 tokens

git-policy-auditor

Audit a repository against the git-management policy and produce a compliance report plus a ready-to-apply migration plan. Read-only — it inspects and proposes, never mutates. Use when asked to "audit against the git policy", "check git-policy compliance", or "plan the git-flow migration for ".

gf-labs/claude-toolbox · 72 tokens

review

Structured code review — diff analysis, readability, correctness, and security. Read-only.

gf-labs/claude-toolbox · 19 tokens

security-reviewer

Read-only, separate-context security reviewer. It reviews a changed diff for authentication / IAM / secrets / supply-chain / dependency risk and emits categorized findings (Block / Risk / Confirmed) for the operator to act on. Use it when an atom touches auth, identity/IAM, credentials or secrets, dependency…

lukasrepublic/agentic-foundry · 108 tokens

pr-reviewer

Read-only, separate-context general code reviewer. It reviews a changed diff for correctness, regressions, maintainability, test coverage, and API/contract hygiene, and emits categorized findings (Block / Risk / Nit) for the operator to act on. Use it when an atom changes code and you want a fresh review pass the…

lukasrepublic/agentic-foundry · 118 tokens

refactor-executor

Craft refactor phase worker. Executes pre-scoped, behavior-preserving refactor specs as atomic commits. Never judges what to refactor. Spawned by the craft refactor phase — do not auto-select.

scolladon/craft · 47 tokens