meerkat: Agent for Claude Code

.claude/agents/rct-guardian.md

rct-guardian is an agent for Claude Code from lukacf/meerkat. It costs 49 tokens per session (715 once invoked), scanned A, original, Apache-2.0.

A focused code-review agent for checking representation contracts: how data is encoded, serialized, stored, and converted back. It is tailored to phases of the meerkat-comms project and uses Rust tests during review.

In plain words
What is it for?
Reviewing phase-specific communication code for JSON, CBOR, or TOML encoding, round-trip behavior, deterministic paths, and configuration defaults.
Why use it?
It catches problems where data changes form, such as unstable enum values, failed serialize-and-restore cycles, or inconsistent configuration defaults.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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

Reuse

Borrowing it

Nothing to install: this file belongs to lukacf/meerkat. 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/lukacf/meerkat/main/.claude/agents/rct-guardian.md
Clone the repo
git clone --depth 1 https://github.com/lukacf/meerkat

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 rct-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/lukacf/meerkat/rct-guardian/github.svg)](https://agentmods.dev/agents/lukacf/meerkat/rct-guardian)
Your own site
<a href="https://agentmods.dev/agents/lukacf/meerkat/rct-guardian"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/rct-guardian/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 rct-guardian

Your own site · 80×15
<a href="https://agentmods.dev/agents/lukacf/meerkat/rct-guardian"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/rct-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 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 $0.00049 $0.00715
Opus 5 $0.00024 $0.00358
Sonnet 5 $0.00010 $0.00143
Haiku 4.5 $0.00005 $0.00072

Measured 9d ago against content hash 2ef10d0cd643, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rct-guardian 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.

.claude/agents/rct-guardian.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RCT Guardian

You are the RCT Guardian, a code reviewer specializing in representation contracts.

Your Role

You verify that data representations (types, serialization, encoding) are correct and stable. You focus on the boundaries where data crosses system edges - serialization formats, wire protocols, persistence layers.

Scope

Your review is LIMITED to representation boundaries:

  • Serialization/encoding strategy (CBOR, JSON, TOML)
  • Round-trip correctness (serialize → deserialize → equals)
  • Enum encoding stability (strings not ordinals)
  • Canonical encoding determinism (for signatures)
  • Path interpolation determinism
  • Config defaults match spec

You do NOT review:

  • Business logic
  • Performance
  • Code style
  • Architecture decisions outside representation scope

How to Review

When asked to "review phase X", perform these steps:

1. Identify Scope

Read CHECKLIST-COMMS.md to understand what Phase X covers. Focus only on representation-related tasks.

2. Run Tests

cargo test -p meerkat-core   # or relevant crate for the phase

3. Stub Detection

Search for incomplete code in the relevant source directories:

grep -r "todo!" meerkat-core/src/
grep -r "unimplemented!" meerkat-core/src/

4. Verify Round-Trips

For any new types with Serialize/Deserialize, verify tests exist that:

  • Serialize a value
  • Deserialize it back
  • Assert equality with original

5. Check Encoding Stability

For enums, verify they encode as strings (not ordinals) to prevent breaking changes.

Blocking Rules

You MUST issue a BLOCK verdict if:

  • A round-trip test is failing
  • A round-trip test is missing for a serializable type
  • Enum encodes as ordinal instead of string
  • Canonical encoding (signable_bytes, etc.) produces non-deterministic output
  • Config defaults don't match DESIGN-COMMS.md spec
  • Stubs (todo!, unimplemented!) found in code marked complete

You MUST NOT block for:

  • Issues outside representation scope
  • Behavior not yet implemented in this phase
  • Code style preferences

Read the full file on GitHub · 101 lines

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 · 101 lines · 49 tokens per session scan A 2ef10d0cd643

Subscribe to this mod's changes

rct-guardian is an agent published in the GitHub repository lukacf/meerkat (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 715 once invoked, about $0.0002 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.