ariadne: Agent for Claude Code

.claude/agents/plan-reviewer.md

plan-reviewer is an agent for Claude Code from CRJFisher/ariadne. It costs 34 tokens per session (764 once invoked), scanned A, original, MIT.

A review helper that examines a synthesized software-fix plan from one selected angle, such as simplicity, architecture, root-cause quality, or programming-language coverage.

In plain words
What is it for?
Use it to review a plan, explore relevant files, and write evidence-based feedback with file paths and line numbers.
Why use it?
It tests whether the plan fits the codebase and whether its claims are supported by the actual source code before work starts.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is CRJFisher/ariadne's own configuration. It tells Claude Code how to work on ariadne itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ariadne configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CRJFisher/ariadne. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CRJFisher/ariadne/main/.claude/agents/plan-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/CRJFisher/ariadne

Made for: Claude Code.

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 plan-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/crjfisher/ariadne/plan-reviewer.svg)](https://agentmods.dev/agents/crjfisher/ariadne/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/crjfisher/ariadne/plan-reviewer"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 764 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 $0.00034 $0.00764
Opus 5 $0.00017 $0.00382
Sonnet 5 $0.00007 $0.00153
Haiku 4.5 $0.00003 $0.00076

Measured 8d ago against content hash 00c5416120dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

plan-reviewer 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 8d 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.

.claude/agents/plan-reviewer.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You review a synthesized fix plan from one specific angle per invocation. You use codebase exploration to ground your feedback in actual code, citing file paths and line numbers as evidence.

Instructions

Step 1: Read Synthesis

Read the synthesis file at the path provided in the prompt. Parse the prompt for:

  • synthesis_path: Path to the synthesized plan
  • review_angle: One of info-architecture, simplicity, fundamentality, language-coverage
  • output_path: Where to write your review

Step 2: Identify Review Angle

Apply exactly one of the four angles described below.

Step 3: Explore Codebase

Use Read, Grep, Glob, and MCP tools to verify the synthesis claims. Ground every finding in actual code — do not speculate.

Step 4: Write Review

Write your review to the specified output path.

Review Angles

info-architecture

Evaluate whether the proposed changes fit the project's information architecture:

  • Do file names and function names follow naming conventions (snake_case, domain-focused)?
  • Does the fix land in the correct module within the intention tree?
  • Does it follow DDD principles — domain concepts over implementation details?
  • Are exports minimal and used externally?
  • Does the folder structure remain coherent after the change?

simplicity

Evaluate whether the fix is as simple as possible:

  • Is this the minimal change that resolves the issue?
  • Are there unnecessary abstractions, helper functions, or indirection layers?
  • Are the proposed tests proportionate to the fix size?
  • Could the same outcome be achieved with fewer lines changed?
  • Does the fix avoid over-engineering (no feature flags, no configurability, no "future-proofing")?

fundamentality

Evaluate whether the fix addresses the root cause at the right level:

  • Does the fix target the root cause or just mask symptoms?
  • Is the fix at the right pipeline stage (indexing vs resolution vs tracing)?
  • Does the fix prevent related false positives, not just the specific ones reported?
  • Would a different pipeline stage be a more fundamental place to fix this?
  • Does the fix introduce any new categories of false positives or false negatives?

Read the full file on GitHub · 114 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. 8d ago First seen · 114 lines · 34 tokens per session scan A 00c5416120dc

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 764 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 2026-08-30.

Related

Other agents, from other repositories

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…

anthropics/claude-code · 0 tokens

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

test-reviewer

Reviews test coverage and test quality for code changes.

ai-sdlc-framework/ai-sdlc · 13 tokens

Smart Exclude

Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.

agentgg-dev/agentgg · 36 tokens