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/skills/rct-methodology/SKILL.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/skills/lukacf/meerkat/rct-methodology)<a href="https://agentmods.dev/skills/lukacf/meerkat/rct-methodology"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/rct-methodology.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 8 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00083 | $0.02915 |
| Opus 5 | $0.00042 | $0.01458 |
| Sonnet 5 | $0.00017 | $0.00583 |
| Haiku 4.5 | $0.00008 | $0.00292 |
Grade A, and why
rct-methodology 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 8d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RCT Methodology Skill
Transform specifications into executable, AI-agent-ready implementation checklists using the RCT (Representation Contract Tests) methodology.
When to Use This Skill
- Creating implementation checklists from specifications or design documents
- Planning phased implementations for complex systems
- When user mentions "RCT", "representation contracts", "Gate 0", or "agent-ready checklist"
- When converting a specification into tasks an AI agent can execute autonomously
Core Principle
Representations first. Behavior second. Internals last.
If core data cannot reliably round-trip across boundaries (API, DB, wire formats), the spec must be challenged before implementation proceeds. RCT prevents the two dominant risks in AI-assisted development:
- Representation mismatch - wire/storage/tool formats don't behave as assumed
- Integration hell - independently "perfect" components don't fit together
The Four RCT Gates (Methodology Gates)
Gate 0 - RCT MUST be green
Representation contracts must pass before any behavior implementation:
- Serialization/encoding for enums/IDs/links
- NULL vs NONE semantics
- Migration/versioning behavior
- Persistence round-trip (write → read → equals)
- External contract shapes
If Gate 0 fails: Stop and revise. Do not proceed.
Gate 1 - E2E scenarios written (red OK)
Define E2E scenarios as black-box flows. Tests may be red but must:
- Start reliably
- Fail for expected reasons (not connection/boot errors)
Gate 2 - Integration choke-points written (red OK)
Integration tests validating cross-component wiring:
- At least two subsystems exercised
- At least one cross-component invariant asserted
Gate 3 - Unit tests as needed
Unit tests support integration tests, not replace them.
Strict Spec → Plan → Checklist Pipeline (REQUIRED)
You MUST follow the strict 2→3→4 pipeline.
See references/strict_pipeline.md for the required structure, file locations, and rules.
Rendering: use the repo-local .rct/scripts/render_checklist.py (scaffolded) to render
.rct/checklist.yaml → .rct/outputs/CHECKLIST.md.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/checklist_template.md 1.3 KB
- references/luka_loop.md 4.0 KB
- references/luka_setup_flow.md 2.4 KB
- references/phase_zero_template.md 1.4 KB
- references/reviewer_prompts.md 18 KB
- references/strict_pipeline.md 2.2 KB
- scripts/luka_scaffold.py 1.3 KB runs code
- scripts/render_checklist.py 2.7 KB runs code
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.
- 8d ago First seen · 309 lines · 83 tokens per session scan A ac4b524688be
rct-methodology is a skill published in the GitHub repository lukacf/meerkat (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 2,915 once invoked, about $0.0004 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 skills, from other repositories
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
deflake
Stabilize a flaky test with a minimal, assertion-preserving fix — never by weakening or deleting the check.
check
Auto-fix lint and formatting, then report types and tests. Run before every commit.