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/xonika9/agent-skills/x9-opencode-sessionsnpx skills add xonika9/agent-skills --skill x9-opencode-sessionsgit clone --depth 1 https://github.com/xonika9/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/xonika9/agent-skills/x9-opencode-sessions)<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-opencode-sessions"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-opencode-sessions.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 | $0.00130 | $0.00644 |
| Opus 5 | $0.00065 | $0.00322 |
| Sonnet 5 | $0.00026 | $0.00129 |
| Haiku 4.5 | $0.00013 | $0.00064 |
Grade A, and why
x9-opencode-sessions 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 5d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode sessions
Use this skill only in OpenCode V2. For child sessions owned by the current parent,
prefer the native subagent tool. Use the Sessions API only to inspect or coordinate a
different root or child branch.
The machine-readable onboarding contract lists external prerequisites.
List only enough session metadata to resolve the request. Start with a supplied session ID when available; otherwise constrain the list by title/search, project, directory, or parent. Stop before sending when the match is ambiguous, and ask the user to select one target.
Run the wrapper for API calls. It emits normalized JSON, shows only text message parts, and keeps reasoning bodies and tool arguments out of the default output. Read the API reference for command forms, the selection rule, and the wait/reconciliation contract.
Sending
prompt is preview-first. Run it without --apply, retain and show its generated
message_id, then dispatch the same ID with --apply only after the user has explicitly
asked to send and one target is unambiguous. The original explicit request is sufficient;
do not add a confirmation step. Never send a live message unless the user requested it.
The wrapper permanently reserves each preview ID and records a one-use local receipt
containing the session ID and a hash of the text; --apply rejects a missing, reused, or
mismatched receipt.
If dispatch times out or its outcome is unknown, do not retry. Reconcile that exact
message_id with message before any further action. Do not delete, rename, move, or
otherwise alter sessions.
wait may be unavailable on a running V2 service. Treat that response as blocked, then
inspect active and paginated messages; never infer completion from the failed wait.
Done
Return the selected session ID, requested text or activity/result, and any child-session
relationship observed. For a sent message, return its message_id and the dispatch or
reconciliation status. A failed API call is BLOCKED or UNKNOWN, not evidence that a
session completed or received a message.
What ships with it
4 files 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.
- 5d ago First seen · 48 lines · 130 tokens per session scan A ed7e655acf41
x9-opencode-sessions is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 9d ago), licensed MIT. It adds 130 tokens to every session and 644 once invoked, about $0.0006 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
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
analytics-tracking
Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data.
aria
Designs the data model, API contracts, and structural foundation of the system.