mcp-contrast: Command for Claude Code

.claude/commands/harness-review.md

harness-review is a command for Claude Code from Contrast-Security-OSS/mcp-contrast. It costs 18 tokens per session (455 once invoked), scanned A, original, Apache-2.0.

A command that reviews a code repository using a harness-engineering playbook. The review checks whether a coding agent can understand the real task, make changes, verify them, and work safely without relying on a person to relay information.

In plain words
What is it for?
Use it to inspect the repository's instructions and documentation, apply the review playbook, and record evidence about how well the repository supports coding-agent work.
Why use it?
It provides a broad, read-only assessment of gaps that may make repository work unclear, unsafe, or difficult to verify.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is Contrast-Security-OSS/mcp-contrast's own configuration. It tells Claude Code how to work on mcp-contrast itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-contrast configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Contrast-Security-OSS/mcp-contrast. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Contrast-Security-OSS/mcp-contrast/main/.claude/commands/harness-review.md
Clone the repo
git clone --depth 1 https://github.com/Contrast-Security-OSS/mcp-contrast

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 harness-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/contrast-security-oss/mcp-contrast/harness-review/github.svg)](https://agentmods.dev/commands/contrast-security-oss/mcp-contrast/harness-review)
Your own site
<a href="https://agentmods.dev/commands/contrast-security-oss/mcp-contrast/harness-review"><img src="https://agentmods.dev/badge/commands/contrast-security-oss/mcp-contrast/harness-review/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-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/contrast-security-oss/mcp-contrast/harness-review"><img src="https://agentmods.dev/badge/commands/contrast-security-oss/mcp-contrast/harness-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 455 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 $0.00018 $0.00455
Opus 5 $0.00009 $0.00228
Sonnet 5 $0.00004 $0.00091
Haiku 4.5 $0.00002 $0.00046

Measured 10d ago against content hash 7d1b4e0e3716, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

harness-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 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.

.claude/commands/harness-review.md · 43 lines

What it actually says

/harness-review

Run Ryan Lopopolo's harness-engineering repository-review playbook against this repository. It is a broad, read-only diagnostic. It asks whether a capable coding agent can recover the real job, make a coherent change, prove the outcome, and operate safely here without using a person as a relay.

An optional focus area may be passed as $ARGUMENTS.

Steps

  1. Locate the corpus by running the snippet in docs/agents/harness.md. That resolves CORPUS_DIR to a read-only checkout pinned to a known commit.

  2. Read $CORPUS_DIR/AGENTS.md. Follow its Application routing and Working loop. It routes a broad assessment to the repository-review playbook.

  3. Read $CORPUS_DIR/playbooks/README.md, then $CORPUS_DIR/playbooks/repository-review.md. Treat the playbook as a scaffold you can adapt, and record any omission with the local evidence that required it.

  4. Run the playbook with this repo as the target. Hold one model and coding-agent configuration constant. Start from this repo's own instructions, CLAUDE.md and docs/agents/, before pulling any corpus thesis. Pull a corpus thesis only when local evidence leaves an owning decision unresolved. Keep the corpus read-only, and adapt its ideas without copying its file layouts, version pins, or fixtures.

  5. Deliver findings ordered by consequence, following the playbook's Findings section. For each, name the invariant at risk, the concrete evidence and owning boundary, why existing proof missed it, and the smallest owning correction.

This command inspects only. It does not authorize changes to the repo. To act on one finding through a bounded change-and-verify loop, run /improve-harness.

If $ARGUMENTS names a focus area, weight the review there while still answering the playbook's outcome questions.

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 · 43 lines · 18 tokens per session scan A 7d1b4e0e3716

Subscribe to this mod's changes

harness-review is a command published in the GitHub repository Contrast-Security-OSS/mcp-contrast (23 stars, last pushed 6d ago), licensed Apache-2.0. It adds 18 tokens to every session and 455 once invoked, about $0.0001 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.