verification-engineer

A read-only agent that designs a plan for checking whether a code change is correct. It considers how widely the change could affect the system and records what cannot currently be verified.

In plain words
What is it for?
Use it to plan tests, checks, and other evidence for a proposed change, and to list remaining verification gaps.
Why use it?
It helps decide what evidence is needed before trusting a change, without confusing a verification plan with a code review or modifying files.

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/nonlinear-xyz/factory-kit/verification-engineer
Clone the repo
git clone --depth 1 https://github.com/nonlinear-xyz/factory-kit
Per session 132 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 192 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 $0.00132 $0.00192
Opus 5 $0.00066 $0.00096
Sonnet 5 $0.00026 $0.00038
Haiku 4.5 $0.00013 $0.00019

Measured 2d ago against content hash e02b5d9eacb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verification-engineer 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.

agents/verification-engineer.md · 11 lines

What it actually says

Apply the preloaded factory-verification-engineer skill to the delegated task. Remain read-only as required by the canonical workflow.

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 · 11 lines · 132 tokens per session scan A e02b5d9eacb3

Subscribe to this mod's changes

verification-engineer is an agent published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 29d ago), licensed MIT. It adds 132 tokens to every session and 192 once invoked, about $0.0007 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

experience-extractor

Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…

claude-world/director-mode-lite · 127 tokens

skill-evolver

Evolution agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase EVOLVE — after experience-extractor produces learning.json, when completion-judge decides EVOLVE, on an --evolve request, or on SHIP for lifecycle review. Applies verified learning to produce improved skill versions and manages…

claude-world/director-mode-lite · 120 tokens

agents-expert

Expert on creating and configuring custom Claude Code agents (subagents). Use PROACTIVELY when the user mentions creating an agent, custom agent, or subagent; when designing specialized agents for project tasks; when troubleshooting agent invocation, tools, or model config; or during /agents-generate. Knows the…

claude-world/director-mode-lite · 138 tokens

completion-judge

Decision-making agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase DECIDE — after the validator writes validation.json, when an iteration cycle completes, or at a manual decision point. Applies the SHIP/FIX/EVOLVE/ABORT threshold rule against verified evidence and writes reports/decision.json.…

claude-world/director-mode-lite · 118 tokens

requirement-analyzer

Deep requirement analysis agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase ANALYZE — starting a new loop session, when the user provides a new requirement or feature request, or when re-analyzing after a failed iteration. Extracts acceptance criteria, a complexity score, an implementation…

claude-world/director-mode-lite · 130 tokens

code-reviewer

Expert code reviewer for quality, security, and best practices. Use PROACTIVELY after writing or modifying code, when reviewing PRs, or before commits. Reports findings by severity (critical/warnings/suggestions) with file:line references and concrete fixes. user: "I just finished the login endpoint — can you check it…

claude-world/director-mode-lite · 104 tokens