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 skills add ngocsangyem/MeowKit --skill developmentgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/development)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/development"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/development/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/skills/ngocsangyem/meowkit/development"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/development.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 | $0.00042 | $0.00494 |
| Opus 5 | $0.00021 | $0.00247 |
| Sonnet 5 | $0.00008 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
mk:development 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 7d 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.
What it actually says
Development Toolkit
Reference guides for implementation: code patterns, TDD enforcement (opt-in), and skill lazy-loading.
When to Use
- During Phase 3 (Build) for implementation guidance
- When the
developeragent needs coding pattern references - For TDD enforcement rules during red/green/refactor cycle (TDD mode only)
Workflow Integration
Operates in Phase 2 (Test) and Phase 3 (Build). Output supports the developer and tester agents.
TDD enforcement (tdd-enforcement.md reference) is OPT-IN as of the TDD-optional migration. Default mode skips RED-phase enforcement; enable with --tdd or MEOWKIT_TDD=1.
References
| Reference | When to load | Content |
|---|---|---|
| code-patterns.md | During implementation | Coding patterns, architecture patterns, file organization |
| tdd-enforcement.md | Phase 2-3 | RED/GREEN/REFACTOR cycle, test-first rules, coverage requirements |
| skill-loader.md | Skill activation | How to load skills on-demand, lazy loading patterns |
Gotchas
- TDD enforcement blocking exploratory prototyping: Strict red-green cycle slows rapid iteration → Default mode (TDD off) is now the right choice for prototypes; opt into
--tddonly when shipping production-quality work - 200-line file rule on generated code: Auto-generated files (migrations, schemas) exceed limit by design → Exempt generated files explicitly in plan constraints
What ships with it
3 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.
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.
- 7d ago First seen · 46 lines · 42 tokens per session scan A d357c8b230bc
mk:development is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 494 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 2026-09-03.
Other skills, from other repositories
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
test-generation
Use when the user asks for tests, mentions TDD, or when new code has been written and needs test coverage.
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.