kkRepo: Agent for Claude Code

.github/agents/protocol-compat-reviewer.md

protocol-compat-reviewer is an agent for Claude Code from klboke/kkRepo. It costs 16 tokens per session (132 once invoked), scanned A, original, Apache-2.0.

A code-review assistant for checking whether kkRepo's repository protocols work with Nexus and official package clients. It examines how hosted, proxy, and group repositories respond to requests.

In plain words
What is it for?
Use it to review HTTP responses, package downloads and uploads, proxy caching, retries, timeouts, deletes, group repository ordering, conflict handling, and compatibility-test coverage.
Why use it?
Protocol changes can break clients through small differences in status codes, headers, redirects, authentication, checksums, or request timing. This review finds concrete compatibility problems and points to the affected files and lines.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is klboke/kkRepo's own configuration. It tells Claude Code how to work on kkRepo 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 kkRepo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to klboke/kkRepo. 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/klboke/kkRepo/main/.github/agents/protocol-compat-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/klboke/kkRepo

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 protocol-compat-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/klboke/kkrepo/protocol-compat-reviewer/github.svg)](https://agentmods.dev/agents/klboke/kkrepo/protocol-compat-reviewer)
Your own site
<a href="https://agentmods.dev/agents/klboke/kkrepo/protocol-compat-reviewer"><img src="https://agentmods.dev/badge/agents/klboke/kkrepo/protocol-compat-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 protocol-compat-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/klboke/kkrepo/protocol-compat-reviewer"><img src="https://agentmods.dev/badge/agents/klboke/kkrepo/protocol-compat-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 132 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 $0.00016 $0.00132
Opus 5 $0.00008 $0.00066
Sonnet 5 $0.00003 $0.00026
Haiku 4.5 $0.00002 $0.00013

Measured 9d ago against content hash 601e1bf6cec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

protocol-compat-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 9d 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.

.github/agents/protocol-compat-reviewer.md · 18 lines

What it actually says

You review kkRepo protocol changes. Focus on hosted, proxy, and group repository compatibility with Nexus and the official package protocol.

Check:

  • HTTP status codes, headers, body shape, redirects, auth challenges, and checksum behavior.
  • Hosted write policy and delete semantics.
  • Proxy cache, negative cache, conditional request, timeout, and retry behavior.
  • Group member ordering and conflict behavior.
  • Compatibility test coverage under compat-test.

Call out concrete file and line references. Prefer actionable findings over style comments.

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. 9d ago First seen · 18 lines · 16 tokens per session scan A 601e1bf6cec4

Subscribe to this mod's changes

protocol-compat-reviewer is an agent published in the GitHub repository klboke/kkRepo (261 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 132 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.

Related

Other agents, from other repositories

imperial-censor

An independent code-review and testing role for Java projects. It writes tests from the project rules before implementation, then checks the finished code against those rules across seven review areas.

TheEterna/api2mcp4j · 72 tokens

code-reviewer

A code-reviewing agent for Java 17, Spring, and MCP projects. It checks recent changes for bugs, design consistency, dependency problems, API compatibility, and project-specific rules, with findings ranked by severity.

TheEterna/api2mcp4j · 64 tokens

dependency-manager

Dependency management, version upgrades, and compatibility specialist.

ChanningLua/prax-agent · 12 tokens

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