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 oxy-hq/oxygen --skill oxy-task-spec-defaultgit clone --depth 1 https://github.com/oxy-hq/oxygenWrote 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/oxy-hq/oxygen/oxy-task-spec-default)<a href="https://agentmods.dev/skills/oxy-hq/oxygen/oxy-task-spec-default"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-task-spec-default/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/oxy-hq/oxygen/oxy-task-spec-default"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-task-spec-default.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 | $0.00124 | $0.00912 |
| Opus 5.5 | $0.00050 | $0.00365 |
| Sonnet 5.5 | $0.00025 | $0.00182 |
| Haiku 4.5 | $0.00012 | $0.00091 |
Grade A, and why
oxy-task-spec-default 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Default long-running work to TaskSpec on the worker fleet
Per Oxy's scaling design (internal-docs/multi-instance-fleet.md, refinement H):
If a feature has any of {long-running compute, periodic schedule, durability requirement, multi-step pipeline}, it should be a TaskSpec on the worker fleet, not a
tokio::spawnin an HTTP handler.
What this means concretely
- New background work defaults to enqueueing a
TaskSpecinagentic_task_queuevia the existing durable orchestrator incrates/agentic/runtime/src/orchestrator/. - New
tokio::spawninside HTTP handlers requires written justification (sub-second fire-and-forget only). - The worker fleet (
oxy worker) drains the queue; the HTTP fleet (oxy serve) only enqueues.
When to default to TaskSpec — quick checklist
- Does it take more than ~5 seconds? → TaskSpec.
- Does it touch the network, LLM APIs, or external services? → TaskSpec.
- Must it survive
oxy serverestart? → TaskSpec. - Will the client poll for status? → TaskSpec.
- Does it run on a schedule? → TaskSpec.
- Could it be retried? → TaskSpec.
If any of these is yes, default to TaskSpec.
How to add a new TaskSpec variant
- Define the variant in the
TaskSpecenum (find it undercrates/agentic/runtime/src/). Carry only what the executor needs; reference indirect data (e.g.,auth_token_refnot the raw token). - Implement the executor branch — invoke the actual work, emit lifecycle events (
Started,Progress(_),Done/Failed). - Wire the enqueue site — replace the
tokio::spawnwithtransport.enqueue(TaskSpec::YourVariant{...}). - Status tracking — domain-specific status columns are updated by the executor as the single writer. Never spawn AND update from the same call site.
- Idempotency — if the same logical work is enqueued twice (e.g., same repo URL + target path), dedupe on a stable key before INSERT.
- Retry policy — set a
TaskPolicywith backoff. Don't retry terminal errors (auth expired, permission denied); do retry transient ones (network blip). - Tests — unit-test the executor happy path + at least one failure mode + idempotency.
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 · 60 lines · 124 tokens per session scan A 2b7b7e380a27
oxy-task-spec-default is a skill published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 124 tokens to every session and 912 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".