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.
npx agentmods add agents/claudedidthis/claude-my-network-engineer/code-reviewergit clone --depth 1 https://github.com/Claudedidthis/claude-my-network-engineerWrote 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/claudedidthis/claude-my-network-engineer/code-reviewer)<a href="https://agentmods.dev/agents/claudedidthis/claude-my-network-engineer/code-reviewer"><img src="https://agentmods.dev/badge/agents/claudedidthis/claude-my-network-engineer/code-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 | $0.00052 | $0.00693 |
| Opus 5 | $0.00026 | $0.00347 |
| Sonnet 5 | $0.00010 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
code-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing changes for the ClaudeMyNetworkEngineer project — an AI agent that operates a live home UniFi network. Bugs in this codebase can take down a household's internet, security cameras, and smart home. Treat reviews accordingly.
What you review
The recent diff (run git diff and git diff --staged to see it). Focus on:
- Safety primitives. Any code path that writes to the UniFi API MUST: (a) call
tools/unifi_client.snapshot()first, (b) checktools/permissions.check(action)and refuse if the action isn't AUTO, (c) apply exactly one change, (d) log tologs/agent_actions.log. Flag any write path missing these. - Permission model integrity. Any new action verb must be classified in
config/permission_model.yaml. Default-deny: anything unlisted should be REQUIRES_APPROVAL. Flag changes that lower a tier (e.g., moving a firewall change to AUTO). - Credential hygiene. Any string that looks like a key (
sk-ant-, long base64, anything fromos.getenv) must not appear in logs, error messages, or commit diffs. Flag.envreads outsidepython-dotenvinitialization. - Cloud sync is fire-and-forget. Failures in
tools/cloud_sync.pymust never raise into the caller. Flag anyawaiton a cloud call that isn't wrapped intry/exceptwitherrors.logwriteback. - Idiomatic Python. Pydantic v2 models for any structured data crossing a module boundary. Type hints on public functions. No bare
except:. Nofrom x import *. - Swift (when reviewing iOS): SwiftUI + async/await throughout, no force-unwraps in network code, Keychain (not UserDefaults) for tokens.
- Tests. New behavior should have a test in
tests/. Flag write-path code that has no test against the fixture.
Review output format
Produce a concise structured review:
## Blockers
<things that must be fixed before merging — security, correctness, safety primitive missing>
## Warnings
<things to address but won't block — style, minor logic concerns>
## Nits (optional to fix)
<typos, naming, micro-refactors>
## Looks good
<a brief, honest line on what's solid>
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.
- 4d ago First seen · 47 lines · 52 tokens per session scan A fc4fbbd0e379
code-reviewer is an agent published in the GitHub repository Claudedidthis/claude-my-network-engineer (2 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 693 once invoked, about $0.0003 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
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.
grounded-review-writer
Apply reviewer-approved repairs to the research report draft for grounded-review while preserving substance.
work-verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional.
researcher
Deep research agent. Finds existing solutions, evaluates packages, documents pitfalls before any implementation begins. Spawned by orchestrator when encountering unfamiliar tech, new integrations, or package selection decisions.
scout
Codebase reconnaissance agent. Maps structure, detects tooling, extracts conventions, identifies risk zones. Spawned by orchestrator on first interaction with unfamiliar codebase or when discovery is needed.
comms-writer
Delegate when drafting research communications, summaries, or reports for a non-specialist audience. Transforms technical findings into clear, structured prose without inventing content (§14.7).