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 joshuadavidthomas/agent-skills --skill roadmapgit clone --depth 1 https://github.com/joshuadavidthomas/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/joshuadavidthomas/agent-skills/roadmap)<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/roadmap"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/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/joshuadavidthomas/agent-skills/roadmap"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/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 | $0.00105 | $0.01704 |
| Opus 5 | $0.00053 | $0.00852 |
| Sonnet 5 | $0.00021 | $0.00341 |
| Haiku 4.5 | $0.00011 | $0.00170 |
Grade A, and why
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 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap
Turn goals, candidate ideas, tickets, findings, and design docs into a high-level view of what's coming up.
A roadmap is direction + prioritization + dependencies. It says what capabilities, outcomes, or strategic tracks are likely next, why they matter, and what must happen before they are real. It is not a wish list, transcript, date promise, backlog dump, sprint plan, or implementation plan.
Default roadmap items are outcomes/capabilities/features. Use Agile-shaped nouns — epics, milestones, phases — only when they clarify sequencing or match the project's vocabulary. Features and epics describe what changes; milestones and phases describe ordering, gates, or release boundaries.
Stay one altitude above writing-plans: decide ordering, slices, gates, and handoffs; do not design unresolved internals or prescribe code. If one item needs product shaping, hand it to brainstorm. If technical choices are unresolved, hand it to design-discussion. If implementation is decided, hand it to writing-plans.
Never modify source code. Write only roadmap artifacts unless the user explicitly asks for downstream artifacts.
Workflow
Phase 1 — Set the altitude
Identify the roadmap's audience and horizon:
- Audience: maintainer, product owner, implementation agents, contributors, leadership, or future-you.
- Horizon: now/next/later by default; use releases, milestones, quarters, or dates only when the user gives a real cadence.
- Scope: whole repo, product area, feature family, technical debt, launch, migration, or agent execution stack.
- Item vocabulary: capability/feature by default; epic, milestone, phase, or initiative only when useful.
- Output: inline answer or durable artifact.
Ask only for missing decisions that would change the roadmap. Ask one question at a time and include your recommended default.
Phase 2 — Recon
Gather source material before prioritizing:
- Read user-provided docs, issues, tickets, ideas, designs, plans,
README,AGENTS.md/CLAUDE.md,CONTEXT.md, ADRs, and existing roadmaps. - If the roadmap comes from
improve, read the selected findings, rejected findings, and dependency notes. - If the roadmap comes from ideation flow, read the relevant
docs/ideas/,docs/tickets/, anddocs/agents/<slug>/artifacts. - If the roadmap is codebase-grounded and no candidates exist, do light read-only direction scouting: TODO/FIXME themes, half-built surfaces, documented-but-undelivered promises, surface asymmetries, high-churn areas, and adjacent capabilities the current architecture makes cheap.
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.
- 9d ago First seen · 130 lines · 105 tokens per session scan A d50ae4636302
roadmap is a skill published in the GitHub repository joshuadavidthomas/agent-skills (50 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,704 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…