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.
curl -O https://raw.githubusercontent.com/lukacf/meerkat/main/.claude/agents/rct-guardian.mdgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/rct-guardian)<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.
<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>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 | $0.00049 | $0.00715 |
| Opus 5 | $0.00024 | $0.00358 |
| Sonnet 5 | $0.00010 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
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.
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
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.
- 9d ago First seen · 101 lines · 49 tokens per session scan A 2ef10d0cd643
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.
Other agents, from other repositories
test-engineer
Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
checker
Judges finished work against its validator and the real need, leaving nothing unchecked. Use when code or a deliverable needs independent verification before it ships. Never edits the work, never implements the fix.
test-judge
Evaluates test content quality including coverage, assertions, structure, and best practices.