opencode

A way to run OpenCode, an open-source coding agent with a command-line interface and interactive terminal screen, as a worker managed by Hermes.

In plain words
What is it for?
Running one-off coding tasks, reviewing or refactoring code, monitoring longer sessions, and executing parallel work in isolated Git worktrees. OpenCode must be installed and connected to at least one model provider.
Why use it?
It gives Hermes another coding agent for implementation, refactoring, review, and longer-running work. Separate work directories can keep parallel tasks from interfering with one another.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/atlasomnia/donna-starter/opencode
Any agent
npx skills add AtlasOmnia/donna-starter --skill opencode
Clone the repo
git clone --depth 1 https://github.com/AtlasOmnia/donna-starter

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 77% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.01869
Opus 5 $0.00009 $0.00934
Sonnet 5 $0.00004 $0.00374
Haiku 4.5 $0.00002 $0.00187

Measured 2d ago against content hash f5d6bc5b9165, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode 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.

Origin

This is a copy

77% identical to opencode — 50 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/autonomous-ai-agents/opencode/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCode CLI

Use OpenCode as an autonomous coding worker orchestrated by Hermes terminal/process tools. OpenCode is a provider-agnostic, open-source AI coding agent with a TUI and CLI.

When to Use

  • User explicitly asks to use OpenCode
  • You want an external coding agent to implement/refactor/review code
  • You need long-running coding sessions with progress checks
  • You want parallel task execution in isolated workdirs/worktrees

Prerequisites

  • OpenCode installed: npm i -g opencode-ai@latest or brew install anomalyco/tap/opencode
  • Auth configured: opencode auth login or set provider env vars (OPENROUTER_API_KEY, etc.)
  • Verify: opencode auth list should show at least one provider
  • Git repository for code tasks (recommended)
  • pty=true for interactive TUI sessions

Binary Resolution (Important)

Shell environments may resolve different OpenCode binaries. If behavior differs between your terminal and Hermes, check:

terminal(command="which -a opencode")
terminal(command="opencode --version")

If needed, pin an explicit binary path:

terminal(command="$HOME/.opencode/bin/opencode run '...'", workdir="~/project", pty=true)

One-Shot Tasks

Use opencode run for bounded, non-interactive tasks:

terminal(command="opencode run 'Add retry logic to API calls and update tests'", workdir="~/project")

Attach context files with -f:

terminal(command="opencode run 'Review this config for security issues' -f config.yaml -f .env.example", workdir="~/project")

Show model thinking with --thinking:

terminal(command="opencode run 'Debug why tests fail in CI' --thinking", workdir="~/project")

Force a specific model only when the user explicitly chooses that provider. Do not default examples to OpenRouter; the user's routing preference is direct/provider-specific unless he says “OpenRouter”.

terminal(command="opencode run 'Refactor auth module' --model anthropic/claude-sonnet-4", workdir="~/project")

Read the full file on GitHub · 230 lines

Changes

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.

  1. 2d ago First seen · 230 lines · 18 tokens per session scan A f5d6bc5b9165

Subscribe to this mod's changes

opencode is a skill published in the GitHub repository AtlasOmnia/donna-starter (102 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 1,869 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 77% identical to opencode, differing in 50 lines, and is treated as a copy.

Related

Other skills, from other repositories

vc-finder

Takes a startup product URL or description, detects the industry and funding stage, identifies 5 comparable funded companies, searches who invested in those companies (Track A), finds VCs who publish investment theses about this space (Track B), and returns a ranked sourced list of relevant investors with deep-dives…

Varnan-Tech/opendirectory · 107 tokens

competitor-pr-finder

Give it your product URL or description. It finds your top 5 competitors, runs three-track PR research across all of them (editorial, podcasts, communities), identifies which channels appear most frequently, looks up the journalist or host for each, and returns a tiered outreach list with story angles and…

Varnan-Tech/opendirectory · 112 tokens

npm-downloads-to-leads

Takes a list of npm package names (yours or competitors'), fetches 12 weeks of daily download data from the npm API, computes a breakout velocity score per package to identify hockey-stick growth, fetches maintainer profiles from the npm registry and GitHub API, and outputs a ranked lead brief for each breakout…

Varnan-Tech/opendirectory · 172 tokens

sdk-adoption-tracker

Given your SDK or library name, searches GitHub code search for public repos that import or require it, classifies each repo as company org, affiliated developer, solo developer, or tutorial noise, scores by adoption signal strength, detects new adopters by date, and outputs a ranked list of who is building on you…

Varnan-Tech/opendirectory · 170 tokens

domain-expired-opportunity-finder

Evaluates expired domain candidates against a target niche, scores them by topical relevance, historical activity level, and history cleanliness, then outputs a ranked shortlist with explainable reasoning and risk flags.

Varnan-Tech/opendirectory · 45 tokens

gh-issue-to-demand-signal

Takes a competitor's public GitHub repo URL, fetches their open issues via the GitHub REST API, filters noise locally, clusters issues into 6 demand categories, computes a demand score per issue and per cluster, and outputs a ranked demand gap report with a GTM messaging brief. Use when asked to scan a competitor's…

Varnan-Tech/opendirectory · 154 tokens