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/cloudposse/atmos/roadmapnpx skills add cloudposse/atmos --skill roadmapgit clone --depth 1 https://github.com/cloudposse/atmosWhat 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 | $0.00080 | $0.02640 |
| Opus 5 | $0.00040 | $0.01320 |
| Sonnet 5 | $0.00016 | $0.00528 |
| Haiku 4.5 | $0.00008 | $0.00264 |
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 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap Maintainer
Use this skill to keep the Atmos roadmap page at /roadmap accurate, up-to-date, and aligned with actual
development progress.
Core Responsibilities
- Update milestone statuses inside
initiatives[].milestones[]when features ship — never promote a milestone intofeatured[]. - Link milestones to changelog entries when announcements are published — but only for user-visible
changes (see "No Changelog Posts for Internal-Only Refactors" below). For the post itself, use the
changelogskill; this skill only owns theroadmap.jslink. - Add new milestones as development plans evolve.
- Update progress percentages based on milestone completion.
- Add new quarters as time progresses.
- Add new initiatives when strategic priorities expand.
- Audit roadmap accuracy against recent releases.
Featured Items: Curated, Max 6, Do Not Modify
The featured: [] array in roadmap.js is a manually curated highlight reel of the top 6 strategic
initiatives only. It is not the changelog and not a list of every shipped milestone.
Hard cap: 6 items. If a featured slot needs to be added, an existing entry must be removed first — and only the user can decide which.
Rule: Never add, remove, or reorder entries in featured unless the user explicitly asks ("add X to
featured", "promote Y to featured", "remove Z from featured"). When you ship a milestone, update its entry
inside initiatives[].milestones[]. You do not mirror it into featured.
Bar for "featured": A featured item represents a strategic, transformative capability — e.g., "Atmos AI", "Cloud Authentication", "Native CI/CD". Per-release improvements, plumbing, and incremental enhancements never qualify, even when they are shipped.
If unsure, ask the user. Do not guess.
No Changelog Posts for Internal-Only Refactors
Changelog posts in website/blog/ are user-facing release announcements. Internal refactors with no
user-visible behavior change do NOT belong in the changelog, even when they are significant engineering
achievements (complexity reduction, test coverage improvements, function decomposition, dependency removal,
etc.).
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 · 310 lines · 80 tokens per session scan A 30750b46e24a
roadmap is a skill published in the GitHub repository cloudposse/atmos (1,367 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 2,640 once invoked, about $0.0004 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
dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
agency-os
Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to…
handoff
Use when managing a two-session handoff — inspecting, picking up, or reviewing a committed handoff package produced by a session=two scope run. The operator interface over the cross-environment handoff lifecycle (plan in one session, build in another, review back in the first). Trigger with /hyperflow:handoff, "list…
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.
fabric-swarm
Creates a self-organizing team of persistent Pi Fabric actors with durable topics, mailboxes, and compare-and-swap tasks. Use for messenger-like collaboration and long-lived delegated work.
dagr-producer
Emit and maintain a dagr run file — a live, contract-valid JSON description of recursive projects, tasks, attempts, gates, evidence, policies, events, and operator-message resolutions that dagr view renders as a DAG. Use when orchestrating agents or tracking multi-step work that a dagr pane should display.