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.
git clone --depth 1 https://github.com/coltonbearden/carrelWrote 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.
[](https://agentmods.dev/agents/coltonbearden/carrel/integration-reviewer)<a href="https://agentmods.dev/agents/coltonbearden/carrel/integration-reviewer"><img src="https://agentmods.dev/badge/agents/coltonbearden/carrel/integration-reviewer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00015 | $0.00117 |
| Sonnet 5 | $0.00006 | $0.00047 |
| Haiku 4.5 | $0.00003 | $0.00023 |
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 7d 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.
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--jsonmode (must be parseable: pipe topython -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.
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.
- 7d ago First seen · 14 lines · 29 tokens per session scan A ff381334d75f
integration-reviewer is an agent published in the GitHub repository coltonbearden/carrel (1 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 233 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 2026-08-31.
Other agents, from other repositories
Test Coverage
Ensure new functionality includes corresponding tests.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
Code
Autonomous task implementation on feature branch. Implements, tests, and commits.
Test
Scenario-based QA agent. Designs and executes acceptance tests from criteria and implementation. Reports pass/fail with evidence — never fixes code.
Validate
Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.