harness-adversarial-reviewer

harness-adversarial-reviewer is an agent for Claude Code from Intense-Visions/harness-engineering. It costs 33 tokens per session (10,460 once invoked), scanned A, original, MIT.

An adversarial code reviewer that imagines how otherwise-correct changes could fail when combined, misused, or given unexpected input.

In plain words
What is it for?
Use it when reviewing completed work or responding to review feedback, especially when ordinary bug, security, and architecture reviews may miss failures caused by combinations of changes.
Why use it?
It finds assumption violations, interactions between components, abuse cases, and chains where one failure spreads to other parts of the system.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Part of the harness-claude plugin — 85 skills, 89 commands, 16 agents, 4 hooks, 4 MCP servers shipped together

Good fit Use it when reviewing completed work or responding to review feedback, especially when ordinary bug, security, and architecture reviews may miss failures caused by combinations of changes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/intense-visions/harness-engineering/harness-adversarial-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/Intense-Visions/harness-engineering

Made for: Claude Code.

Or install harness-claude, the plugin that ships this one along with the rest of its 85 skills, 89 commands, 16 agents, 4 hooks, 4 MCP servers.

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 harness-adversarial-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-adversarial-reviewer/github.svg)](https://agentmods.dev/agents/intense-visions/harness-engineering/harness-adversarial-reviewer)
Your own site
<a href="https://agentmods.dev/agents/intense-visions/harness-engineering/harness-adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-adversarial-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for harness-adversarial-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/intense-visions/harness-engineering/harness-adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-adversarial-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,460 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 $0.00033 $0.10460
Opus 5 $0.00016 $0.05230
Sonnet 5 $0.00007 $0.02092
Haiku 4.5 $0.00003 $0.01046

Measured 10d ago against content hash 181ca98e3440, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

harness-adversarial-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 10d 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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

.antigravity-extension/agents/harness-adversarial-reviewer.md · 874 lines

How it starts

The opening of the file, as written. The whole thing — 874 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Sit between bug, security, and architecture. Hunt for failure modes that single-pattern agents miss — assumptions the diff relies on but does not enforce, two correct pieces that misbehave together, adversarial inputs the diff does not anticipate, and (at Deep depth) single failures that cascade through downstream callers. Never re-flag findings owned by the existing 4 agents. Emit ReviewFinding[] with domain: 'bug', subagent: 'adversarial', and numeric confidence per the shared confidence rubric.

Skills

  • harness-code-review

Steps

  1. Execute harness-code-review skill (manual)
  2. Execute harness-code-review skill (on_pr)

Methodology

Harness Code Review

Multi-phase code review pipeline — mechanical checks, graph-scoped context, parallel review agents, cross-agent deduplication, and structured output with technical rigor over social performance.

When to Use

  • When performing a code review (manual invocation or triggered by on_pr / on_review)
  • When requesting a review of completed work (see Role A at the end of this document)
  • When responding to review feedback (see Role C at the end of this document)
  • NOT for in-progress work (complete the feature first)
  • NOT for rubber-stamping (if you cannot find issues, look harder or state confidence level)
  • NOT for style-only feedback (leave that to linters and mechanical checks)

Argument Resolution

When invoked by autopilot (or with explicit arguments), resolve paths before starting:

  1. Session slug: If session-slug argument provided, set {sessionDir} = .harness/sessions/<session-slug>/. Pass to gather_context({ session: "<session-slug>" }). All handoff writes go to {sessionDir}/handoff.json.
  2. Commit range: If commit-range argument provided (e.g., abc123..HEAD), use as diff scope in Phase 2 MECHANICAL and Phase 7 OUTPUT. Otherwise, auto-detect from git environment.

When no arguments are provided (standalone invocation), session slug is unknown — omit from gather_context, fall back to global .harness/ paths. Diff scope auto-detected.

Read the full file on GitHub · 874 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. 10d ago First seen · 874 lines · 33 tokens per session scan A 181ca98e3440

Subscribe to this mod's changes

harness-adversarial-reviewer is an agent published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 10,460 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

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens