Atmosphere is a portable runtime for running AI agents on the Java Virtual Machine through a common interface across multiple AI frameworks. It serves agents as real-time services with streaming, tool calls, approvals, and governance over several transport protocols. Catalogue add-ons extend the agent runtime's workflow and operation.
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/atmosphere/atmosphere/strategy-agentnpx skills add Atmosphere/atmosphere --skill strategy-agentgit clone --depth 1 https://github.com/Atmosphere/atmosphereWrote 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/atmosphere/atmosphere/strategy-agent)<a href="https://agentmods.dev/skills/atmosphere/atmosphere/strategy-agent"><img src="https://agentmods.dev/badge/skills/atmosphere/atmosphere/strategy-agent.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 | $0.00036 | $0.00212 |
| Opus 5 | $0.00018 | $0.00106 |
| Sonnet 5 | $0.00007 | $0.00042 |
| Haiku 4.5 | $0.00004 | $0.00021 |
Grade A, and why
strategy-agent 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.
What it actually says
Strategy Agent
You are a market strategy analyst. You perform SWOT analysis, competitive positioning, and go-to-market strategy based on research findings.
You evaluate market timing, entry strategies, and competitive dynamics to produce actionable strategic recommendations.
Skills
- SWOT analysis (strengths, weaknesses, opportunities, threats)
- Competitive positioning and differentiation strategy
- Market timing assessment (entry, growth, maturity phases)
- Go-to-market strategy recommendations
Guardrails
- Base analysis on provided research data, not assumptions
- Present balanced view — opportunities AND threats
- Qualify recommendations with confidence level
- Flag when research data is insufficient for strong conclusions
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 · 33 lines · 36 tokens per session scan A c272346a1c0c
strategy-agent is a skill published in the GitHub repository Atmosphere/atmosphere (3,808 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 212 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 2026-08-30.
Other skills, from other repositories
check-code-attribution
Per-file check of vendored code attribution in the current branch diff, including license headers, THIRDPARTYNOTICES.md entries, and compatibility with Sentry's licensing policy.
create-java-pr
Create a pull request in sentry-java. Use when asked to "create pr", "prepare pr", "prep pr", "open pr", "ready for pr", "prepare for review", "finalize changes". Handles branch creation, code formatting, API dump, committing, pushing, PR creation, changelog, and stacked PRs.
test
Run tests for a specific SDK module. Use when asked to "run tests", "test module", "run unit tests", "run system tests", "run e2e tests", or test a specific class. Auto-detects unit vs system tests. Supports interactive mode.
plugin-code-review-orchestrated
Orchestrates a code review of the spring-plugin repository through scope/context passes, routing, domain reviewer subskills, and per-artifact validation. Use when asked to review a PR, diff, commit, branch, module, or file set, to run a full orchestrated review, or to produce a validated review report.
review-async-lifecycle
Normative reviewer for EDT safety, coroutines, cancellation, read/write actions, disposal, listeners and async lifecycle in the explyt spring-plugin. Use during orchestrated code review when the diff touches threading, background tasks, read or write actions, listeners, MessageBus, Disposable ownership or progress…
github-issue-manager
Classifies a user request as Bug, Compatibility, Feature, Question, or Task for the explyt/spring-plugin GitHub repo, lightly researches the relevant codebase, searches similar existing issues, and either reports an existing issue or creates a correctly titled and labeled one following the repository issue forms. Use…