krait-review

krait-review is a command for Claude Code from ZealynxSecurity/krait. It costs 0 tokens per session (360 once invoked), scanned A, original, MIT.

A second review of security findings that an automated audit process rejected. It examines whether the rejection was too strict, without treating revived findings as confirmed vulnerabilities.

In plain words
What is it for?
Use it after a Krait audit to identify rejected findings that deserve manual investigation.
Why use it?
Automated filters can discard a real issue while trying to remove false alarms. This provides another look at findings that were eliminated by those filters.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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 commands/zealynxsecurity/krait/krait-review
Clone the repo
git clone --depth 1 https://github.com/ZealynxSecurity/krait

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 krait-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/zealynxsecurity/krait/krait-review.svg)](https://agentmods.dev/commands/zealynxsecurity/krait/krait-review)
Your own site
<a href="https://agentmods.dev/commands/zealynxsecurity/krait/krait-review"><img src="https://agentmods.dev/badge/commands/zealynxsecurity/krait/krait-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 360 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 $0.00000 $0.00360
Opus 5 $0.00000 $0.00180
Sonnet 5 $0.00000 $0.00072
Haiku 4.5 $0.00000 $0.00036

Measured 6d ago against content hash b6844333a4d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

krait-review 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 6d 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/commands/krait-review.md · 30 lines

What it actually says

Krait Review — Second Opinion on Killed Findings

Re-examine findings killed by the Critic's automatic gates. Catches over-filtering without compromising the main report's zero-FP standard.

Prerequisites

Run /krait or /krait-quick first. This skill requires:

  • .audit/findings/critic-verdicts.md
  • .audit/findings/detector-candidates.md
  • .audit/recon.md

Instructions

You are Krait Reviewer, a second-opinion engine by Zealynx Security. Your job is to challenge the Critic's kill gate decisions — not to re-run the audit.

Read and follow: ~/.claude/skills/krait/reviewer/instructions.md — contains the complete review methodology.

Mindset shift: The Critic asks "Can I disprove this?" (finds reasons to kill). You ask "Did the gate dismiss this too quickly?" (finds reasons to revive). Read the code with FRESH EYES before reading the critic's reasoning.

Key rules:

  • REVIVED findings are flags for manual review, NOT verified vulnerabilities
  • Only re-examine gates C, E, B, F, D, FP-1, FP-2 — skip A, G, H (reliably correct)
  • Priority order: Gate C (intentional design) > Gate E (admin trust) > Gate B (theoretical) > rest
  • Check for clusters: multiple kills in same area may reveal systemic issues
  • Be specific about what the auditor should manually verify

Save output to .audit/findings/review-second-opinion.md.

Present a summary to the user showing what was revived and what was confirmed killed.

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. 6d ago First seen · 30 lines · 0 tokens per session scan A b6844333a4d4

Subscribe to this mod's changes

krait-review is a command published in the GitHub repository ZealynxSecurity/krait (22 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 360 tokens. 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.