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 nyquistgit 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/nyquist)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/nyquist"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/nyquist/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/nyquist"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/nyquist.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 | $0.00094 | $0.00849 |
| Opus 5 | $0.00047 | $0.00425 |
| Sonnet 5 | $0.00019 | $0.00170 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade A, and why
mk:nyquist 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nyquist — Test-to-Requirement Coverage Mapping
Maps plan acceptance criteria to test files. Identifies coverage gaps where requirements exist but no corresponding test validates them.
When to Use
- Phase 2 (Test): After tester writes initial tests, verify all acceptance criteria are covered
- Phase 4 (Review): As part of test coverage dimension, verify no gaps
- User says "check test coverage", "are all requirements tested", "coverage gaps"
- Before Gate 2: verify implementation matches plan
Workflow
- Load plan — Read
tasks/plans/YYMMDD-name/plan.md, extract acceptance criteria - Scan tests — Glob for test files (
**/*.test.*,**/*.spec.*,**/test_*.*) - Map criteria → tests — For each acceptance criterion, search test descriptions/names for matching keywords
- Identify gaps — Criteria with no matching test = coverage gap
- Produce report — Structured output with mapping table and gap list
Output Format
## Nyquist Coverage Report: [Plan Name]
### Requirement-to-Test Mapping
| # | Acceptance Criterion | Test File | Test Name | Status |
|---|---------------------|-----------|-----------|--------|
| 1 | [criterion text] | src/auth.test.ts | "should authenticate user" | COVERED |
| 2 | [criterion text] | — | — | GAP |
| 3 | [criterion text] | src/api.test.ts | "returns 404 for missing" | COVERED |
### Coverage Summary
- **Total criteria:** N
- **Covered:** N (N%)
- **Gaps:** N
### Gap Details
1. **[criterion text]** — No test found. Suggested test: [brief description]
2. **[criterion text]** — No test found. Suggested test: [brief description]
### Recommendation
[PASS — all criteria covered | WARN — N gaps found, suggest adding tests]
Matching Strategy
- Keyword matching: Extract key nouns/verbs from acceptance criteria, search in test
describe/it/teststrings - File path matching: If criterion mentions "auth", search in
**/auth*test* - Fuzzy matching: If exact match fails, check for semantic equivalents (e.g., "login" ≈ "authenticate")
- Manual override: If no match found, ask user to confirm the gap is real (not a naming mismatch)
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 · 91 lines · 94 tokens per session scan A 2a7b162e8672
mk:nyquist is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 849 once invoked, about $0.0005 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
phx-work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after phx-plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
lab:autoresearch
Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.
codex-loop
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.