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 Hadi99K/AGENT_SKILLS --skill create-roadmapgit clone --depth 1 https://github.com/Hadi99K/AGENT_SKILLSWrote 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/hadi99k/agent_skills/create-roadmap)<a href="https://agentmods.dev/skills/hadi99k/agent_skills/create-roadmap"><img src="https://agentmods.dev/badge/skills/hadi99k/agent_skills/create-roadmap/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/hadi99k/agent_skills/create-roadmap"><img src="https://agentmods.dev/badge/skills/hadi99k/agent_skills/create-roadmap.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 | $0.00056 | $0.03030 |
| Opus 5.5 | $0.00022 | $0.01212 |
| Sonnet 5.5 | $0.00011 | $0.00606 |
| Haiku 4.5 | $0.00006 | $0.00303 |
Grade A, and why
create-roadmap 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 4d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🗺️ Create Roadmap (progress.md)
What I Do
- Analyze App Ideas & Specs: Takes a user's raw app concept, feature list, or architecture brief and dissects it into an execution-ready master roadmap.
- Generate
progress.md: Builds a comprehensive, phased tracking file (progress.md) featuring granular checklists, UI/UX tasks, data models, edge cases, settings, monetization, and store publishing. - Enforce Complete App Lifecycles: Ensures critical non-feature phases are never overlooked (theming/settings, legal/privacy, monetization gating, app security/obfuscation, splash/onboarding, and store deployment).
- Establish Long-Term Evolution: Structures the document with post-launch update sprints (
## Updates), future backlogs (## Future Plans), and immediate punchlists (## Next To-Do).
When to Use Me
- Right after the user describes a new app concept, feature set, or pitch.
- When starting Phase 1 of a new project after running
project-scaffold. - When an existing project needs a comprehensive, professional master roadmap.
- When the user asks: "create progress.md", "plan out the app phases", "break down this app idea into a roadmap", or "make a roadmap like Floatkit".
🏛️ The Floatkit Roadmap Architecture
A production-grade app is never just a list of features. It spans a 15-Phase Progressive Lifecycle:
┌─────────────────────────────────────────────────────────────┐
│ APP LIFECYCLE PROGRESSION │
├─────────────────────────────────────────────────────────────┤
│ 🔌 Phase 1: Core Foundation & Runtime Infrastructure │
│ 🗄️ Phase 2: Data Architecture, Storage & State Flow │
│ 🎨 Phase 3: Shell Layout, Design Tokens & Base Navigation │
│ 📦 Phases 4–N: Modular Core Features (One phase per module) │
│ 📱 Phase N+1: Companion Dashboard / Home Interface │
│ ⚙️ Phase N+2: Settings, Customization & Data Management │
│ ℹ️ Phase N+3: About, Support, FAQs & Developer Contact │
│ 🛡️ Phase N+4: Legal, Compliance, Privacy & Disclosures │
│ ⭐ Phase N+5: Monetization, Paywall & Feature Gating │
│ 🔐 Phase N+6: Security, Integrity, Obfuscation & Hardening │
│ ❇️ Phase N+7: Branding, App Icon, Splash & Onboarding │
│ 🚀 Phase N+8: Production Polish, Testing & Store Publishing │
│ ─────────────────────────────────────────────────────────── │
│ 🔄 Updates: Post-Launch Feature Updates (v1.1, v1.2, ...) │
│ 🔮 Future Plans: Ideation Backlog │
│ 🛠️ Next To-Do: Active Bugfixes & Immediate Punchlist │
└─────────────────────────────────────────────────────────────┘
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.
- 4d ago First seen · 275 lines · 56 tokens per session scan A f4061a954e5b
create-roadmap is a skill published in the GitHub repository Hadi99K/AGENT_SKILLS (3 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 3,030 once invoked, about $0.0002 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 2026-10-18.
Other skills, from other repositories
openspec-bulk-archive-change
Archive multiple completed OpenSpec changes at once. Use when archiving several parallel changes. Also use for a plural archive request - "openspec bulk-archive", "opsx bulk-archive", "openspec archive all", or "openspec archive these changes".
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
stakeholder-communication-and-status-updates
Guides writing narrative-style stakeholder status updates and strategy memos instead of bullet-point decks, grounded in Amazon's 6-page narrative memo discipline. Use when the user asks to "write a status update," "draft a weekly update for stakeholders," "write a project update email," "prepare a 6-pager," "turn…
planning-and-task-breakdown
Breaks an existing spec or clear requirement into a dependency-ordered, sized task list with checkpoints and parallelization notes. Use when a task feels too large to start, when scope needs estimating, or when work can be split across parallel agents/sessions. For a single lightweight plan document for one request…
spec-driven-development
Writes a structured, human-reviewed specification before any code, deriving implementation from that written contract rather than from a vague request. Use when starting a new project or feature with no spec yet, when requirements are ambiguous or only exist as an idea, or before an architectural decision on a change…
constraint-driven-development
Use when an Android project has no written quality bar, when the user says "set up constraints" or "define our standards", when coverage, performance, or accessibility should become enforced gates instead of per-PR arguments, when an agent keeps silencing checks or skipping tests to get to green, or when a threshold…