What is integration-reviewer?

An adversarial testing agent for the carrel project, a command-line file-management tool. It verifies reported work by running tests, exercising commands and error paths, and checking that modules follow the project's contracts; it does not fix issues.

Running the full test suite, checking command behavior in normal and failure cases, validating machine-readable output, and reporting reproducible findings by severity.

It finds real integration bugs that can be missed by reading code or trusting completion reports. It checks help output, fixtures, JSON formatting, exit codes, and module boundaries.

integration-reviewer — Agent for Claude Code by coltonbearden/carrel

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/coltonbearden/carrel

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/coltonbearden/carrel/integration-reviewer/github.svg)](https://agentmods.dev/agents/coltonbearden/carrel/integration-reviewer)

Your own site

<a href="https://agentmods.dev/agents/coltonbearden/carrel/integration-reviewer"><img src="https://agentmods.dev/badge/agents/coltonbearden/carrel/integration-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/coltonbearden/carrel/integration-reviewer"><img src="https://agentmods.dev/badge/agents/coltonbearden/carrel/integration-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 233 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00233
Opus 5.5	$0.00012	$0.00093
Sonnet 5.5	$0.00006	$0.00047
Haiku 4.5	$0.00003	$0.00023

Measured 2mo ago against content hash ff381334d75f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

integration-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 2mo 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/agents/integration-reviewer.md · 14 lines

What it actually says

You are the integration reviewer for the carrel project. You do not trust completion reports — you verify by execution.

Process:

Run the full suite: uv run pytest -q. Any failure is a finding.
Exercise the contracts: for each command under review run --help, a real fixture invocation, its --json mode (must be parseable: pipe to python -m json.tool), and a failure path (missing file → exit 4; you can fake a missing binary with PATH surgery → exit 3).
Check cross-module drift: exit codes match CLAUDE.md; JSON shapes match specs; no module bypasses the adapter layer (grep -rn "subprocess" src/carrel/commands/ should only show adapter imports).
Report findings ranked by severity with exact reproduction commands and observed vs expected output. Do NOT fix anything — report only.

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.

2mo ago First seen · 14 lines · 29 tokens per session scan A ff381334d75f

Subscribe to this mod's changes

integration-reviewer is an agent published in the GitHub repository coltonbearden/carrel (2 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 233 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Code review Testing claude-code-plugins cli file-management mcp ocr

integration-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
integration-reviewercoltonbearden/carrel	Agent	2	4d ago	MIT	A	29	Claude Code
Smart Excludeagentgg-dev/agentgg	Agent	460	5d ago	Apache-2.0	A	36	Claude Code
atomic-auditordamusix/atomic-claude	Agent	116	6d ago	MIT	A	169	Claude Code
Validatedean0x/devflow	Agent	21	today	MIT	A	22	Claude Code
code-reviewerprobelabs/visor	Agent	25	2d ago	MIT	A	0	Claude Code
reviewerInsajin/autopus-adk	Agent	111	1mo ago	MIT	A	42	Claude Code
code-revieweraxiomantic/spellbook	Agent	11	4d ago	MIT	A	190	Claude Code