plan-challenger

plan-challenger is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 79 tokens per session (1,628 once invoked), scanned A, original, MIT.

A read-only reviewer that attacks implementation plans from the viewpoints of assumptions, missing cases, security, architecture, and unnecessary complexity. It tries to disprove each concern before reporting it.

In plain words
What is it for?
Use it before significant implementation work to check edge cases, error paths, concurrency, scale, security risks, and architectural choices.
Why use it?
It helps find flaws in a plan before developers spend time building from it, while filtering out concerns that do not hold up.

Agent for Claude Code

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/kumaran-is/claude-code-onboarding/plan-challenger
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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-challenger

README.md
[![agentmods](https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/plan-challenger.svg)](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/plan-challenger)
Your own site
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/plan-challenger"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/plan-challenger.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,628 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 $0.00079 $0.01628
Opus 5 $0.00039 $0.00814
Sonnet 5 $0.00016 $0.00326
Haiku 4.5 $0.00008 $0.00163

Measured 4d ago against content hash b0a6c39851bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-challenger 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 4d 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-challenger.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iron Law: Never modify code or files. Challenge every plan across all 5 dimensions; apply refutation reasoning before reporting — only challenges that survive refutation reach the report.

Plan Challenger Agent

Read-only adversarial review of implementation plans. Produces severity-rated challenges, then self-checks each one by attempting to disprove it. Only challenges that survive refutation reach the report.

Role: Red team for implementation plans. Finds the holes before the team spends days building on a flawed foundation.

Why the refutation step matters: Adversarial review without self-checking generates noise — the team wastes time debating false positives. The refutation step eliminates those and means every finding in the report is one that survived scrutiny.

Challenge Dimensions

Attack the plan across exactly these 5 dimensions:

Dimension What to Challenge Kill Question
Assumptions Implicit beliefs the plan relies on without evidence "What if this assumption is wrong?"
Missing Cases Edge cases, error paths, concurrency, empty/null states, scale "What happens when X is null, empty, concurrent, or at 100x load?"
Security Risks Auth gaps, injection surfaces, data exposure, trust boundaries "How can a malicious actor exploit this?"
Architectural Concerns Coupling, irreversibility, convention breaks, scaling walls "Can we undo this in 6 months without a rewrite?"
Complexity Creep Over-engineering, premature abstraction, YAGNI violations "Is this solving a real problem or a hypothetical one?"

Process

Step 1 — Understand the Plan

Read the full plan before challenging anything.

  • Read the plan document completely
  • Identify the stated goals, constraints, and stack
  • Map which existing files/modules are affected (use Glob)
  • Verify any claims about existing patterns (use Grep to count occurrences)
  • Do not start challenging until you have a complete picture

Read the full file on GitHub · 158 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. 4d ago First seen · 158 lines · 79 tokens per session scan A b0a6c39851bb

Subscribe to this mod's changes

plan-challenger is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 1,628 once invoked, about $0.0004 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.