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 plan-creatorgit 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/plan-creator)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/plan-creator"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/plan-creator/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/plan-creator"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/plan-creator.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 | $0.00093 | $0.04886 |
| Opus 5.5 | $0.00037 | $0.01954 |
| Sonnet 5.5 | $0.00019 | $0.00977 |
| Haiku 4.5 | $0.00009 | $0.00489 |
Grade A, and why
mk:plan-creator 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 1mo 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Creator
Public surface: classify → inspect → capture missing decisions → draft → validate → Gate 1. Produces plan.md overview + phase-XX detail files; execution, existing-plan audits, visual rendering, archive, and durable-memory capture stay with their existing owners.
When to Use
Activate when:
- User runs
/mk:plan [task]or/mk:cook [task] - Non-trivial task (> 2 files OR > 1h OR architectural decisions)
- User supplies ≥2 upstream reports/specs (office-hours, brainstorming, planning-engine, confluence-spec, intake output…) → step-00.5 consolidates them into a Plan Intake Packet before planning (see
references/plan-intake-packet.md) - User supplies a design evidence packet (e.g. from
mk:figma) → plan consumes it (viewport/state ACs, critical-action validation matrix, phaseblocked_on:for high-risk flow ambiguity), never re-analyzes the design source (seereferences/design-evidence-consumption.md) - Gate 1 requires a plan before Phase 3
- Green-field product build ("build a kanban app", "create a SaaS dashboard", "make a retro game maker") → step-00 auto-detects and offers
--product-level - Existing-plan audit →
mk:validate-plan; archive → lifecycle CLI; visual rendering →mk:visual-plan. - Hard/deep plan creation still runs its built-in red-team and validation interview before Gate 1. These are design-quality gates, not standalone subcommands, and must never be routed away.
- Compatibility aliases:
/mk:plan archive→ archive workflow;/mk:plan red-team {path}→ standalone red-team workflow;/mk:plan validate {path}→ standalone validation workflow.
Standalone aliases route to their compatibility references; they do not replace hard/deep red-team or validation. --html routes to mk:visual-plan.
Skip when:
/mk:fixwith complexity=simple (Gate 1 exception)mk:scale-routingreturns workflow=one-shot + zero blast radius
What ships with it
59 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.
- assets/plan-template.md 1.9 KB
- assets/product-spec-template.md 4.3 KB
- assets/spike-plan-template.md 3.4 KB
- prompts/personas/plan-assumption-destroyer.md 2.8 KB
- prompts/personas/plan-failure-mode-analyst.md 3.2 KB
- prompts/personas/plan-scope-complexity-critic.md 2.8 KB
- prompts/personas/plan-security-adversary.md 3.2 KB
- references/adr-generation.md 3.0 KB
- references/advice-checkpoints.md 6.4 KB
- references/anthropic-example-plan.md 11 KB
- references/archive-workflow.md 4.8 KB
- references/cold-start-context-brief.md 3.3 KB
- references/deep-mode.md 2.3 KB
- references/design-evidence-consumption.md 4.5 KB
- references/failure-catalog.md 1.4 KB
- references/gate-1-approval.md 3.4 KB
- references/gotchas.md 2.8 KB
- references/ops-metrics-design.md 3.2 KB
- references/output-standards.md 2.6 KB
- references/parallel-mode.md 1.8 KB
- references/phase-template.md 8.6 KB
- references/plan-intake-packet.md 4.8 KB
- references/plan-mutation-protocol.md 3.3 KB
- references/plan-organization.md 980 B
- references/red-team-standalone.md 2.3 KB
- references/research-phase.md 839 B
- references/scope-challenge.md 2.0 KB
- references/solution-design-checklist.md 2.5 KB
- references/solution-evaluation.md 796 B
- references/task-management.md 9.8 KB
- references/tdd-mode.md 1.9 KB
- references/two-approach-mode.md 2.1 KB
- references/validate-standalone.md 2.3 KB
- references/validation-questions.md 3.6 KB
- references/verification-roles.md 6.0 KB
- references/visual-plan-integration.md 11 KB
- references/whole-plan-sweep.md 9.4 KB
- references/worked-example-stripe-billing.md 8.1 KB
- references/workflow-models/bugfix-model.md 1.3 KB
- references/workflow-models/feature-model.md 1.4 KB
- references/workflow-models/refactor-model.md 1.1 KB
- references/workflow-models/security-model.md 1.0 KB
- scripts/check-product-spec.sh 2.1 KB runs code
- scripts/validate-plan.py 11 KB runs code
- step-00-5-intake-packet.md 3.0 KB
- step-00-scope-challenge.md 13 KB
- step-01-research.md 2.0 KB
- step-02-codebase-analysis.md 2.9 KB
- step-03-draft-plan.md 15 KB
- step-03a-product-spec.md 8.7 KB
- step-04-semantic-checks.md 8.6 KB
- step-05-red-team.md 12 KB
- step-06-validation-interview.md 7.6 KB
- step-07-gate.md 4.7 KB
- step-08-hydrate-tasks.md 6.8 KB
- step-08b-html-render.md 3.0 KB
- step-09-post-plan-handoff.md 5.5 KB
- workflow-fast.md 3.7 KB
- workflow.md 12 KB
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.
- 1mo ago First seen · 252 lines · 93 tokens per session scan A f6ad4fc92dc3
mk:plan-creator is a skill published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 4,886 once invoked, about $0.0004 per session on Opus 5.5. 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
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
react-patterns
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…
design-review
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…