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 assimovt/productskills --skill roadmap-planninggit clone --depth 1 https://github.com/assimovt/productskillsWrote 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/assimovt/productskills/roadmap-planning)<a href="https://agentmods.dev/skills/assimovt/productskills/roadmap-planning"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/roadmap-planning/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/assimovt/productskills/roadmap-planning"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/roadmap-planning.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 | $0.00794 |
| Opus 5 | $0.00030 | $0.00397 |
| Sonnet 5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
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 11d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build roadmaps organized by outcomes, not feature lists. A roadmap answers "what problems are we solving and in what order?" — not "what features will we ship and when?" Dates on a roadmap beyond 6 weeks are fiction. Treat them that way.
Now / Next / Later
Three time horizons, decreasing in certainty:
Now (Committed — this cycle)
- Currently in progress or about to start
- Fully shaped: problem defined, solution scoped, appetite set
- Team assigned, expected to ship this cycle
- 1-3 items maximum
Next (Shaped — next 1-2 cycles)
- Problem validated, solution partially shaped
- Not yet assigned to a team
- May change based on what we learn from "Now" items
- 3-5 items maximum
Later (Raw — ideas worth exploring)
- Problems we believe are real but haven't validated
- No solution shaped yet
- Will be promoted to "Next" when evidence supports it, or killed
- No limit, but prune quarterly
Roadmap Items Are Outcomes, Not Features
Each roadmap item is framed as a problem to solve or an outcome to achieve:
Bad (feature-list roadmap):
- Build team collaboration features
- Add CSV export
- Redesign settings page
Good (outcome-based roadmap):
- Reduce time-to-first-value for team signups from 15 min to under 5 min
- Enable users to get their data out without contacting support
- Reduce settings-related support tickets by 50%
The solution emerges during shaping, not during roadmap planning.
Shape Up Cycle Planning
For teams using Shape Up cycles:
- Betting table: Leadership reviews shaped pitches and bets on what to build next cycle. Not everything gets picked.
- Cool-down: 1-2 weeks between cycles for bug fixes, exploration, and shaping future work.
- No carry-over: Work that doesn't ship in a cycle is not automatically carried over. It must be re-pitched.
Presenting the Roadmap
Keep it to one page or one screen. If your roadmap needs scrolling, it's too detailed.
Format as a simple table:
| Horizon | Outcome | Evidence | Status |
|---|---|---|---|
| Now | Reduce onboarding drop-off to under 30% | 5 interviews, 60% current drop-off | In progress, week 2/3 |
| Next | Enable self-serve data export | 12 support tickets/month | Shaped, needs team |
| Later | Multi-workspace support | 3 enterprise prospects requested | Unvalidated |
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.
- 11d ago First seen · 83 lines · 59 tokens per session scan A bfbf7617b4e8
roadmap-planning is a skill published in the GitHub repository assimovt/productskills (68 stars, last pushed 6mo ago), licensed MIT. It adds 59 tokens to every session and 794 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 2026-08-30.
Other skills, from other repositories
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…
execute-fleet
Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…