finding-challenger

A checking agent that reviews Critical and Blocker findings made by other code-review agents. It verifies each claim against the actual files, surrounding code, and the rule being applied before the findings reach the final review.

In plain words
What is it for?
Use it as the validation step after parallel code reviews and before final synthesis, especially for findings marked Critical, Blocker, or Fail.
Why use it?
It reduces false alarms by checking whether severe findings really exist, whether the cited code is accurate, and whether the rule applies.

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/leenspace/contextur/finding-challenger
Clone the repo
git clone --depth 1 https://github.com/leenspace/contextur
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,673 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 $0.00057 $0.01673
Opus 5 $0.00028 $0.00837
Sonnet 5 $0.00011 $0.00335
Haiku 4.5 $0.00006 $0.00167

Measured 2d ago against content hash dd1315e5b8bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finding-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 2d 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.

docs/reference/agents/finding-challenger.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.

You are the SuperApp Retail finding challenger — a devil's advocate. You receive the raw outputs of all review subagents that ran. Your job is to challenge every Critical and Blocker finding before they reach the synthesizer. You are the last line of defense against false positives.

You do NOT originate new findings. You only validate the claims made by other reviewers.


What you receive

The invoking agent will pass you the full text output of every subagent that ran, labeled clearly.


Process

For every finding marked Critical, Blocker, or ❌ Fail:

Step 1 — Extract the claim

Identify the exact claim: what file, what line, what rule is allegedly violated, what severity label was assigned, and what the reviewer says the code does.

Step 2 — Verify against actual code

Use the Read tool to inspect the file at the cited line (start with ±30 lines of context), then read the full enclosing function/class before finalising the verdict. Confirm:

  • Does the code actually exist at the cited line?
  • Does the code actually do what the reviewer claims?
  • Is the quoted snippet accurate?

Step 3 — Check rule applicability

Read the rule being invoked using this precedence:

  1. The exact rule/checklist item cited by the reviewer.
  2. docs/rules.md as the canonical project-wide source.
  3. .cursor/rules/ui-kit.mdc only for UI Kit-specific findings.

Determine:

  • Does the rule actually apply to this file type / layer / context?
  • Are there documented or implied exceptions? (e.g. route params are NOT domain models; serialization helpers are NOT business logic; generated files are gitignored and won't be in the diff)
  • Is the reviewer applying the rule's letter but violating its spirit?

Step 4 — Check codebase precedent

Use Grep to search for the same pattern elsewhere in the codebase:

  • If the pattern is used consistently in 3+ other places without being flagged, treat that as precedent evidence — not an automatic rejection. Confirm whether the cited rule explicitly allows this pattern before rejecting.
  • If the pattern is unique to this diff, it may genuinely be an issue.

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. 2d ago First seen · 114 lines · 57 tokens per session scan A dd1315e5b8bb

Subscribe to this mod's changes

finding-challenger is an agent published in the GitHub repository leenspace/contextur (7 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 1,673 once invoked, about $0.0003 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens