opencode-agent
Run OpenCode CLI as an independent coding agent across its provider catalog, capture its session, or dispatch its profiled GitHub PR reviewer.
Skill by ejarmand
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ejarmand-opencode-agent
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/opencode-agent
What's inside
- Skill name
opencode-agent- Description
- Run OpenCode CLI as an independent coding agent across its provider catalog, capture its session, or dispatch its profiled GitHub PR reviewer.
- License
- MIT
- Instructions
- 102 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (5)
- SKILL.md
- openai.yaml · agents/
- server.js · plugins/decline-long-retry/
- config.json · profiles/github-pr-reviewer/
- run-profiled.sh · scripts/
SKILL.md (first lines)
# OpenCode Agent Run `opencode run` from the intended workspace with one selected `provider/model`. Read `/cross-provider-agent` first; backend choice and authority doctrine live there. ## Check the transport This skill targets OpenCode 2 (verified against 2.0.28). Treat installed help as authoritative: ```bash opencode --version opencode run --help opencode auth list ``` OpenCode accepts stored provider credentials and providers' conventional environment variables. ## Choose the provider route The `provider/` prefix decides who sees the prompt. - Paid models: use `opencode/<model>` (OpenCode Zen). Zen's paid models follow its zero-retention policy; OpenAI and Anthropic models there are retained 30 days. - Free, trial and Contributor models on Zen collect data. Use them only where repository policy allows. ## Start and monitor a worker ```bash cd /absolute/path/to/workspace && \ opencode run --format json --model opencode/<model> "TASK" ``` Pass the task as a plain argument, not after `--`: OpenCode 2 sends anything after `--` twice. Select a variant in the model, as `opencode/<model>#high`. `run` attaches to the user's background OpenCode service unless given `--standalone`. Capture `sessionID` from the first JSON event. Resume the same session with `--session SESSION_ID`; add `--fork` when follow-up work must branch from it. On completion require a successful process exit and no error event or failed tool. OpenCode 2 exits nonzero when a step fails or the run is interrupted, and does not always emit a final `step_finish`. The calling agent owns monitoring and termination. ## Profiled dispatch For running limited opencode sessions based on particular profiles use ```bash /absolute/path/to/opencode-agent/scripts/run-profiled.sh \ --workspace /absolute/path/to/workspace \ --profile github-pr-reviewer \ --model opencode/deepseek-v4-flash \ -- "REVIEW_TASK" ``` Add `--variant high` before `--` when the review calls for high effort. The runner passes it to OpenCode in the model, as `opencode/<model>#high`. The prompt must not start with `-`. `--agent` picks another primary agent from the profile; the runner refuses subagents, which OpenCode would otherwise silently swap for its default agent. The runner starts OpenCode with `--standalone`, a private server inside the sandbox, so a profiled run never attaches to the user's background service and its config and credentials. OpenCode sees no user, project or system (`/etc/opencode`) config or plugins; the only plugin is the runner's own, below. The runner mounts the workspace read-only at its own path, and a linked worktree's repository git dir with it, so `git` and `gh` work inside as they do outside; `gh` needs no `--repo`. OpenCode prints nothing while it waits on a provider, so the runner bounds those waits: - `--provider-timeout SECONDS` (default 120) limits the wait for response headers and between stream chunks. OpenCode retries a timed-out request a few times, then emits an error event and exits nonzero. Timeouts the profile sets for that provider win. - A run with no event for `--idle-timeout SECONDS` (default 1800) is stopped with exit 75, after the runner prints what each OpenCode process was waiting on (its stdin, kernel wait channel and TCP connections) and the log tail. Treat 75 as a failed run and report those lines rather than retrying blindly. - OpenCode 2 waits out a provider's rate limit or overload (429, 503, 529) silently, honoring retry-after up to 15 minutes a retry. The runner's plugin lets it wait at most `--rate-limit-grace SECONDS` (default 60); a longer retry-after fails the run, and the runner prints the provider's error and exits 76. Retry later or dispatch another provider. ### available profiles **github-pr-reviewer**: `profiles/github-pr-reviewer/config.json` encodes the provider-neutral contract from `/cross-provider-agent`, including the `code-review` skill and its two named child agents.
From ejarmand/skills, MIT.
More from ejarmand/skills
- 0.592score
cursor-agent
ejarmand
Run Cursor Agent CLI as an independent coding agent for implementation, investigation, planning, or review in a local workspace.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
pr-ping-pong
ejarmand
Drive an issue or pull request through alternating rallies of implementation and cross-provider review until it is review-clean.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
file-pr
ejarmand
Structure GitHub pull requests, issues, and comments.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
code-review
ejarmand
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
improve-codebase-architecture
ejarmand
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
codex-agent
ejarmand
Run Codex CLI as an independent coding worker for implementation, investigation, planning, or review, then monitor and verify its result.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
fix-steering
ejarmand
Analyze Codex history for interruptions, corrections, and user steering that indicate agent errors.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
claude-agent
ejarmand
Run Claude Code CLI headless as an independent coding agent for implementation, investigation, planning, or review in a local workspace.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
codebase-design
ejarmand
Shared vocabulary for designing deep modules, and home of the unified code standard (STANDARD.md).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
html-visualization
ejarmand
Build, revise, and evaluate browser-rendered HTML visualizations for concepts, systems, codebases, architectures, workflows, timelines, comparisons, and other…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
cross-provider-agent
ejarmand
Dispatch a bounded task to a Claude, Codex, Cursor, or OpenCode CLI agent with least authority.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
implement
ejarmand
Implement a prepared spec or set of tickets.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 20
- Last commit (this folder)
- Oct 14, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ejarmand/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ejarmand
- 0.592score
cursor-agent
ejarmand
Run Cursor Agent CLI as an independent coding agent for implementation, investigation, planning, or review in a local workspace.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
pr-ping-pong
ejarmand
Drive an issue or pull request through alternating rallies of implementation and cross-provider review until it is review-clean.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
file-pr
ejarmand
Structure GitHub pull requests, issues, and comments.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
code-review
ejarmand
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
improve-codebase-architecture
ejarmand
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
codex-agent
ejarmand
Run Codex CLI as an independent coding worker for implementation, investigation, planning, or review, then monitor and verify its result.
SkillBFreshness: B★ 1Claude Code +9
Cite this page
opencode-agent skill. Agent Mart. https://agentmart.dev/skills/ejarmand-opencode-agent (last updated 2026-10-24)