Agent skill

Opencode

by laude-institute in laude-institute/headlong

Delegate a bounded coding task to OpenCode and review its retained candidate, patch, verification, and trajectory evidence.

Apache-2.0Auto-check passed

Install Opencode

skills CLI
$ npx skills add laude-institute/headlong --skill opencode -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install laude-institute/headlong opencode --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/laude-institute/headlong.git skills-src && mkdir -p .claude/skills && cp -r skills-src/contrib/opencode/skill .claude/skills/opencode && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
opencode
GitHub stars
1.2k
Token cost
~383 tokens
SKILL.md length
148 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Delegate a bounded coding task to OpenCode and review its retained candidate, patch, verification, and trajectory evidence.

  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Opencode is an agent skill from laude-institute/headlong. Delegate a bounded coding task to OpenCode and review its retained candidate, patch, verification, and trajectory evidence.

Its SKILL.md is about 380 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down. The licence is Apache-2.0.

Example prompts

  • “/opencode”

What it can do on your machine

Read from SKILL.md and the folder at commit 2738148. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Opencode loads about 383 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~383

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from laude-institute/headlong at commit 2738148, republished under its Apache-2.0 licence (© laude-institute). 148 words, ~383 tokens.

Download SKILL.mdSave it as .claude/skills/opencode/SKILL.md (or your agent's skills folder).
name
opencode
description
Delegate a bounded coding task to OpenCode and review its retained candidate, patch, verification, and trajectory evidence.

Use this capability during the existing act action for a bounded coding task with a meaningful independent verification command. Write the requirements to a task file and invoke the installed wrapper:

bash
"$IDENTITY_DIR/extensions/opencode/bin/coding-agent" \
  --repo /absolute/path/to/repository --task-file /absolute/path/to/task.md \
  --verify 'project-specific-check' --out /absolute/path/to/new-artifacts

Inspect the status, candidate commit, patch, verification output, and child trajectory reference. A passing test does not establish that the requirements are satisfied: review the diff and behavior the test did not cover. Record rejection and concrete feedback in the trajectory when inadequate. For a revision, use a fresh output directory and retain earlier candidate/review references. Leave satisfactory candidates ready for human review with accepted:false. Enablement does not authorize merge, push, deployment, or acceptance.

The operator may disable this skill between wakes. A remembered absolute path will then reject new calls; do not bypass that control. Worktrees and model permissions are not an OS sandbox. See the installed package's README for runtime configuration and retained artifact cleanup.

© laude-institute, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in contrib/opencode/skill of laude-institute/headlong.

Open the folder on GitHubat commit 2738148

Compare with similar skills

Opencode next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Opencode compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Opencode this skilllaude-institute/headlong1.2k—~383Automated safety check: PassApache-2.0
Delegating To Agentssickn33/agentic-awesome-skills47k1 repos~1kAutomated safety check: PassMIT
Opencode Delegatesickn33/agentic-awesome-skills47k1 repos~2.8kAutomated safety check: PassMIT
Cline Delegatesickn33/agentic-awesome-skills47k1 repos~1.7kAutomated safety check: PassMIT
Codex Delegatesickn33/agentic-awesome-skills47k1 repos~2.6kAutomated safety check: PassMIT
Grok Delegatesickn33/agentic-awesome-skills47k1 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • Delegating To Agents

    sickn33/agentic-awesome-skills

    Delegate bounded work to other AI agents while preserving context, ownership, and progress checks.

    47k GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Opencode Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the OpenCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    Auto-check passed
  • Cline Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the Cline CLI (cline) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Codex Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the OpenAI Codex CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check passed
  • Grok Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the Grok Build CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check passed
  • Omp Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to Oh My Pi (omp) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~2.4k tokens
    Auto-check passed

More from laude-institute/headlong

All 10 skills in this repo
  • Shellm Architecture Reference

    laude-institute/headlong

    Explains how shellm's bash-based recursive LLM shell fits together - its core engine, identity system, memory, skills and trajectory log.

    1.2k GitHub stars~2k tokensUpdated today
    Auto-check: notes
  • ShellLM Skill Author

    laude-institute/headlong

    Scaffolds new ShellLM skills with the right frontmatter, directory layout and agent-facing writing style, so an agent can extend its own capabilities.

    1.2k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Web Research With curl

    laude-institute/headlong

    Looks things up online from the shell with curl: fetching pages, searching DuckDuckGo's HTML endpoint, stripping tags for readable text and pulling JSON APIs.

    1.2k GitHub stars~362 tokensUpdated today
    Auto-check passed
  • Google Workspace CLI

    laude-institute/headlong

    Drives Google Drive, Gmail, Calendar, Sheets, Docs and Chat from the shell with the gws CLI, including its sign-in, flags, helper commands and safety rules.

    1.2k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Obsidian

    laude-institute/headlong

    Read, write, search, and manage notes in an Obsidian vault. An agent skill from laude-institute/headlong.

    1.2k GitHub stars~880 tokensUpdated today
    Auto-check passed
  • Slack

    laude-institute/headlong

    Talk with people on Slack — recognize slack- senders and reach them via chat reply

    1.2k GitHub stars~831 tokensUpdated today
    Auto-check passed

Questions about Opencode

What does Opencode do?

Delegate a bounded coding task to OpenCode and review its retained candidate, patch, verification, and trajectory evidence. Opencode is an agent skill from laude-institute/headlong. Delegate a bounded coding task to OpenCode and review its retained candidate, patch, verification, and trajectory evidence.

How do I install Opencode in Claude Code?

Run `npx skills add laude-institute/headlong --skill opencode -a claude-code`. Or copy the skill folder (contrib/opencode/skill in laude-institute/headlong) into .claude/skills/opencode in your project. Claude Code loads it when a task matches its description.

How do I install Opencode in Codex?

Run `npx skills add laude-institute/headlong --skill opencode -a codex`. Or copy the skill folder (contrib/opencode/skill in laude-institute/headlong) into .agents/skills/opencode in your project. Codex loads it when a task matches its description.

Can I use Opencode in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add laude-institute/headlong --skill opencode -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/opencode, .gemini/skills/opencode, .github/skills/opencode and .opencode/skills/opencode in your project.

What does Opencode need to run?

SKILL.md names no scripts, command-line tools or credentials: Opencode is instructions for the agent only.

Does Opencode access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Opencode safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Opencode use?

Opencode is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Opencode use?

About 383 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Opencode?

Skills that share tags, products or a category with Opencode: Delegating To Agents (sickn33/agentic-awesome-skills, 47k stars), Opencode Delegate (sickn33/agentic-awesome-skills, 47k stars), Cline Delegate (sickn33/agentic-awesome-skills, 47k stars) and Codex Delegate (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Opencode?

laude-institute (a GitHub organization) maintains it in laude-institute/headlong, which has 1,213 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

Source: laude-institute/headlong on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.