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 agentmods add skills/flinedev/plankit/roadmap-planningnpx skills add FlineDev/PlanKit --skill roadmap-planninggit clone --depth 1 https://github.com/FlineDev/PlanKitWrote 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/flinedev/plankit/roadmap-planning)<a href="https://agentmods.dev/skills/flinedev/plankit/roadmap-planning"><img src="https://agentmods.dev/badge/skills/flinedev/plankit/roadmap-planning.svg" alt="Measured on agentmods" 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 | $0.02499 |
| Opus 5 | $0.00047 | $0.01249 |
| Sonnet 5 | $0.00019 | $0.00500 |
| Haiku 4.5 | $0.00009 | $0.00250 |
Grade A, and why
roadmap-planning 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 6d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap Planning
Triage ideas into versioned releases, clarifying requirements and making key decisions along the way.
Config Preamble
Before any operation, locate the PlanKit folder and read its config:
- Check if
PlanKit/exists in the project root. If not, checkplan-kit/. - If neither exists, tell the user: "No PlanKit folder found. Run
/plankit:initto set up PlanKit first." - Read
.config.jsonfrom the PlanKit folder to get the naming convention and split threshold.
Determine file paths:
- Ideas:
PlanKit/Ideas.mdorPlanKit/Ideas/(split mode) — UpperCamelCase- Or:
plan-kit/ideas.mdorplan-kit/ideas/— kebab-case
- Or:
- Roadmap:
PlanKit/Roadmap.mdorPlanKit/Roadmap/(split mode) — UpperCamelCase- Or:
plan-kit/roadmap.mdorplan-kit/roadmap/— kebab-case
- Or:
- Progress:
PlanKit/Progress.mdorplan-kit/progress.md
Roadmap Triage Workflow
This is the primary workflow — turning ideas into a versioned roadmap:
- Read Ideas file — load all current ideas (handle split mode: read the index file then relevant topic files)
- Read existing Roadmap — understand what versions and features already exist
- Detect current project version:
- Check for Xcode project (Marketing Version in pbxproj)
- Check Package.swift for version
- Check git tags (
git tag --sort=-v:refname | head -5) - Check package.json version field
- If none found, ask the user what version they're planning
- Investigate the codebase — read AGENTS.md, CHECKPOINT.md, README.md, and other project docs to understand what's already implemented, what's changed, and what context is relevant to roadmap planning.
If the roadmap already has content (review + triage):
- Present the current state — show a summary: roadmap versions with feature counts, ideas grouped by theme with idea counts. Include observations from your codebase investigation (e.g., features that may already be implemented, items that are content tasks rather than code, ideas that relate to existing roadmap features).
- Discuss and refine conversationally — don't force rigid per-idea triage. Instead:
- Point out roadmap items that appear done, misplaced, or outdated
- Suggest structural improvements (version scope, ordering, merging small items)
- Ask about version scope and goals — what should each version represent?
- Use AskUserQuestion for concrete choices (e.g., "Should X move to v2.0?") but keep the overall flow conversational
- Ask targeted clarifying questions about the biggest unknowns (1-3 per feature)
- When designing AskUserQuestion options, prefer mixed/progressive options over exclusive ones (e.g., "All in priority order" not just one exclusive choice). Include scope-fluid options like "Try all, defer complex ones."
- Always present the current version plan summary before asking about future versions or next priorities. Never ask "what comes after vX?" without first showing what vX contains.
- After review, offer to triage remaining ideas — present untriaged ideas that weren't discussed yet. Ask which to pull into existing or new versions.
What ships with it
1 file 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.
- 6d ago First seen · 150 lines · 94 tokens per session scan A e8f362f5100c
roadmap-planning is a skill published in the GitHub repository FlineDev/PlanKit (20 stars, last pushed 4mo ago), licensed MIT. It adds 94 tokens to every session and 2,499 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…