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 validate-plangit 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/validate-plan)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/validate-plan"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/validate-plan/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/validate-plan"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/validate-plan.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 | $0.00059 | $0.01628 |
| Opus 5 | $0.00030 | $0.00814 |
| Sonnet 5 | $0.00012 | $0.00326 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
mk:validate-plan 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Validation — 8-Dimension Quality Check
Audits an approved plan against 8 dimensions to catch gaps before implementation begins. Does NOT replace Gate 1 (human approval), modify plans, or route edits itself. If it finds an Insert or Split mutation is needed, the planner performs it and returns to Gate 1 for re-approval; Skip and Reorder changes require notification plus audit log.
For green-field harness sprints (generator↔evaluator loop), use
mk:sprint-contractinstead.mk:validate-planoperates on plans frommk:plan-creator(cook flow only).
When to Use
- After Gate 1 approval, before Phase 2 (Test)
- When
/mk:cookdetects a COMPLEX task (auto-suggested) - When user wants to stress-test a plan before committing to implementation
- When user says "validate this plan", "check my plan", "is this plan complete"
8 Validation Dimensions
| # | Dimension | Pass Criteria | Common Failure |
|---|---|---|---|
| 1 | Scope Clarity | In-scope and out-of-scope sections are explicit and non-overlapping | Vague scope: "improve the auth system" without boundaries |
| 2 | Acceptance Criteria | Every criterion is binary (pass/fail), not subjective | Subjective: "should feel fast" vs binary: "response < 200ms" |
| 3 | Dependencies Resolved | All external dependencies identified with status (available/blocked) | Missing: needs DB migration but not listed as dependency |
| 4 | Risks Identified | At least 1 risk flag with mitigation strategy | No risks listed (every plan has risks; zero = not evaluated) |
| 5 | Architecture Documented | Technical approach references existing patterns or includes ADR | "We'll figure out the architecture during implementation" |
| 6 | Test Strategy | Test approach covers acceptance criteria; edge cases identified | "We'll add tests after" (violates TDD) |
| 7 | Security Considered | Auth, data access, input validation addressed (or explicitly N/A) | No mention of security for a feature handling user data |
| 8 | Effort Estimated | Time/complexity estimate with confidence level | No estimate or "it depends" without qualification |
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 · 133 lines · 59 tokens per session scan A 25807a2c5bcf
mk:validate-plan is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,628 once invoked, about $0.0003 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
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
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.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
rfi-management
Complete RFI (Request for Information) management system. Create, track, route, and analyze RFIs with automatic notifications and response deadline tracking.
daily-report-generator
Automatically generate daily construction reports from field data, worker inputs, weather, and progress photos. Creates professional PDF reports.