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/tomzx/agents/create-roadmapnpx skills add tomzx/agents --skill create-roadmapgit clone --depth 1 https://github.com/tomzx/agentsWhat 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 | $0.00032 | $0.01866 |
| Opus 5 | $0.00016 | $0.00933 |
| Sonnet 5 | $0.00006 | $0.00373 |
| Haiku 4.5 | $0.00003 | $0.00187 |
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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Roadmap
Defines the project's roadmap as a single context-level artifact: the initiatives the project is betting on, sequenced across horizons (Now / Next / Later) and tied to the objectives in goals.md.
Other skills consult the roadmap when deciding what to work on next. Without a roadmap, prioritization is ad hoc: every issue is ranked in isolation, sequencing constraints are invisible, and there is no shared view of what is committed versus exploratory. A plan (plan.md) describes how to build one feature; the roadmap describes what to build and in what order across the whole project.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. .sdlc/context/project-overview.md(must exist, for purpose and scope)..sdlc/context/goals.md(strongly recommended; every initiative aligns to an objective and key result. If absent, note that alignment cannot be checked and flag it as an open question)..sdlc/context/roadmap.md(optional; if present, revise rather than replace, per Revision Mode below).- Existing features under
.sdlc/features/and the open issue backlog (optional, to roll up into initiatives and detect orphaned work).
Steps
- Read
.sdlc/context/project-overview.mdfor purpose, scope, and stakeholders. - Read
.sdlc/context/goals.mdif present; these objectives anchor every initiative. Read.sdlc/context/service-levels.mdif present, for reliability constraints that bound what can be committed to Now. - Inventory in-flight and planned work: scan
.sdlc/features/and, if the backlog is in GitHub, list open issues withghx issue list --state open. - Confirm the horizon model with the user if not already stated: prefer Now / Next / Later (the default) over date-based quarters, because horizons avoid the false precision of dates. Note the current period.
- Identify the recurring themes for this period, each tied to a
goals.mdobjective. - Group work into initiatives (a coherent bet that moves a metric), not individual tickets. For each initiative capture the objective it advances, an owner, the hypothesis, scope, dependencies, confidence, and a success signal tied to a key result or KPI.
- Place each initiative in the right horizon:
- Now: committed, in-flight, or starting this horizon. Fully scoped.
- Next: planned for the following horizon. Roughly scoped.
- Later: exploratory, hypothesis-level, low confidence.
- Map sequencing and dependencies between initiatives (hard, soft, external), and render a Mermaid Gantt chart in the Timeline section visualizing the initiatives across the horizons, anchored to the current period. Use the horizons as
sectiongroups, approximate spans (not hard dates), andafter <id>to show dependencies. - State Not Now explicitly: deferred work and the condition that would promote it.
- Record capacity and hard constraints if known (team capacity, regulatory deadlines, frozen periods).
- Set a review cadence and today's date.
- Write the output to
.sdlc/context/roadmap.md. If it already exists, revise per Revision Mode.
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.
- 2d ago First seen · 106 lines · 32 tokens per session scan A ceffe74aabea
create-roadmap is a skill published in the GitHub repository tomzx/agents (5 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 1,866 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.