Agent skill

Opengantry

by iii-hq in iii-hq/workers

OpenGantry iii worker. An agent skill from iii-hq/workers.

Apache-2.0Auto-check passed

Install Opengantry

skills CLI
$ npx skills add iii-hq/workers --skill opengantry -a claude-code

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

GitHub CLI
$ gh skill install iii-hq/workers opengantry --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/iii-hq/workers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/opengantry/skills .claude/skills/opengantry && 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
opengantry
GitHub stars
113
Token cost
~705 tokens
SKILL.md length
305 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

OpenGantry iii worker. An agent skill from iii-hq/workers.

  • An iii project needs deterministic promote gates: gantry::verify runs the repo gate command
  • SKILL.md covers When to Use, Preferred stack (do not…, Boundaries and Functions, plus 1 more section
  • Calls git
  • Gantry::middleware blocks promote-class calls until a verdict token matches the current mission

What it does

Opengantry is an agent skill from iii-hq/workers. OpenGantry iii worker. Use when an iii project needs deterministic promote gates: gantry::verify runs the repo gate command, gantry::middleware blocks promote-class calls until a verdict token matches the current mission.

Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is Apache-2.0.

When your agent uses it

  • An iii project needs deterministic promote gates: gantry::verify runs the repo gate command
  • Gantry::middleware blocks promote-class calls until a verdict token matches the current mission

Example prompts

  • “/opengantry”

What it can do on your machine

Read from SKILL.md and the folder at commit ebfe027. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Opengantry loads about 705 tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 305 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~705

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 iii-hq/workers at commit ebfe027, republished under its Apache-2.0 licence (© iii-hq). 305 words, ~705 tokens.

Download SKILL.mdSave it as .claude/skills/opengantry/SKILL.md (or your agent's skills folder).
name
opengantry
description
OpenGantry iii worker. Use when an iii project needs deterministic promote gates: gantry::verify runs the repo gate command, gantry::middleware blocks promote-class calls until a verdict token matches the current mission.

opengantry

Call gantry::verify with an absolute repo_root and active mission. The worker runs the repo's declared gate command via the OpenGantry kernel and mints a verdict token bound to that mission revision.

When to Use

  • Promote-class functions on a governed port should stay blocked until verify passes.
  • You want unattended agents without an unattended git push — pair with approval-gate for human-held judgement calls.

Preferred stack (do not reinvent)

Install and use these ecosystem workers instead of writing custom equivalents:

NeedUseDo not
Machine promote gategantry::verify + gantry::middlewareCustom ::verify / ::promote functions
Human judgement on shipapproval-gate (approval::gate)Inline hold logic in your app worker
Git land / mergeworktree::land (+ shell for test gates)Custom myapp::deploy / ::merge
GitHub operationsgithub::*Raw gh shell from agent code
Public governed portrbac-proxy with gantry::middlewareRolling your own auth middleware
Verify completion eventsSubscribe to gantry::verdictPolling verify JSON for side effects

Canonical pipeline: worktree::create → agent work → gantry::verify → worktree::land (with verdict_token in context). Promote-class suffixes (::deploy, ::merge, ::publish, ::apply, ::push, ::promote) require a token whose claims match the mission on disk.

Boundaries

  • Session admission (session::auth) — that is the adopter's IdP worker.
  • Writing .gitagent/ law — Planner commits missions. The worker process does not.
  • Leases — durable at <repo>/.gitagent/leases.json (0600), not in state:: KV.

Functions

  • gantry::verify — run verifyMission for the active mission; a pass binds the mission to the lease and mints the verdict token
  • gantry::middleware — governed-port gate; promote-class calls need a token whose claims are recomputed at promote time
  • gantry::on-function-registration — block gantry:: / opengantry:: namespace squatting and reserved suffixes
  • gantry::on-trigger-registration — block triggers bound into the gantry:: namespace
  • gantry::on-trigger-type-registration — always denied
  • gantry::verdict — trigger type; fires after every verify (pass or fail) for audit/notifications

Bootstrap (host only)

If .gitagent is missing in the target repo, run gantry init on the host (not from the sandboxed worker), then commit a mission via the Planner workflow.

© iii-hq, 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 opengantry/skills of iii-hq/workers.

Open the folder on GitHubat commit ebfe027

Compare with similar skills

Opengantry 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.

Opengantry compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Opengantry this skilliii-hq/workers113—~705Automated safety check: PassApache-2.0
Promotealirezarezvani/claude-skills28k1 repos~1.1kAutomated safety check: PassMIT
Worker Visualizernexu-io/open-design100k—~998Automated safety check: PassApache-2.0
Agent Worker Specialistruvnet/ruflo74k2 repos~1.4kAutomated safety check: PassMIT
Loop Workerruvnet/ruflo74k—~297Automated safety check: PassMIT
Cloudflare Workerssickn33/agentic-awesome-skills47k2 repos~2.7kAutomated safety check: PassMIT

Similar skills

  • Promote

    alirezarezvani/claude-skills

    Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.

    28k GitHub starsUsed in 1 repo~1.1k tokens
    Agent WorkflowsAuto-check passed
  • Worker Visualizer

    nexu-io/open-design

    A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas…

    100k GitHub stars~998 tokensUpdated yesterday
    Auto-check passed
  • Agent skill for worker-specialist - invoke with $agent-worker-specialist

    74k GitHub starsUsed in 2 repos~1.4k tokens
    Auto-check passed
  • Loop Worker

    ruvnet/ruflo

    Run Ruflo background workers using Claude Code native /loop scheduling

    74k GitHub stars~297 tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Cloudflare Workers

    sickn33/agentic-awesome-skills

    Build and deploy edge functions with Cloudflare Workers and Wrangler.

    47k GitHub starsUsed in 2 repos~2.7k tokens
    Backend & APIsAuto-check passed
  • Deterministic Design

    sickn33/agentic-awesome-skills

    Render the UI and prove it's balanced + usable: a deterministic layout audit (centroid / optical-center / pixel-oracle balance via explicit math + annotated screenshot) plus a vision-judged Nielsen…

    47k GitHub starsUsed in 1 repo~736 tokens
    Frontend & DesignAuto-check passed

More from iii-hq/workers

All 19 skills in this repo
  • Cron

    iii-hq/workers

    Schedule any registered function on a 6- or 7-field cron expression with the standalone cron worker.

    113 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Email

    iii-hq/workers

    Send and read email from the iii engine — SMTP send, IMAP read, and real-time IDLE push as a subscribable trigger type.

    113 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • HTTP

    iii-hq/workers

    Expose registered functions as HTTP endpoints with the standalone http worker.

    113 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Kanban

    iii-hq/workers

    File-backed kanban board: create, read, move and comment on tickets by key or uuid, assign agent profiles, and wake on comments through the kanban:comment trigger instead of polling.

    113 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Pubsub

    iii-hq/workers

    DEPRECATED (will be removed in an upcoming release; migration guide https://iii.dev/docs/upgrading/migrate-from-streams).

    113 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Release Sync

    iii-hq/workers

    Organize worker release tags into Linear release waves — one team document plus one release/<date label per same-day batch of worker releases, with shipped MOT issues labeled and linked.

    113 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

Questions about Opengantry

What does Opengantry do?

OpenGantry iii worker. An agent skill from iii-hq/workers. Opengantry is an agent skill from iii-hq/workers. OpenGantry iii worker.

When should I use Opengantry?

Opengantry fits situations like: an iii project needs deterministic promote gates: gantry::verify runs the repo gate command; gantry::middleware blocks promote-class calls until a verdict token matches the current mission.

How do I install Opengantry in Claude Code?

Run `npx skills add iii-hq/workers --skill opengantry -a claude-code`. Or copy the skill folder (opengantry/skills in iii-hq/workers) into .claude/skills/opengantry in your project. Claude Code loads it when a task matches its description.

How do I install Opengantry in Codex?

Run `npx skills add iii-hq/workers --skill opengantry -a codex`. Or copy the skill folder (opengantry/skills in iii-hq/workers) into .agents/skills/opengantry in your project. Codex loads it when a task matches its description.

Can I use Opengantry 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 iii-hq/workers --skill opengantry -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/opengantry, .gemini/skills/opengantry, .github/skills/opengantry and .opencode/skills/opengantry in your project.

What does Opengantry need to run?

Going by SKILL.md and its folder, Opengantry needs the command-line tools its instructions call (git).

Does Opengantry access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Opengantry 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 Opengantry use?

Opengantry 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 Opengantry use?

About 705 tokens (SKILL.md is roughly 2.8k 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 Opengantry?

Skills that share tags, products or a category with Opengantry: Promote (alirezarezvani/claude-skills, 28k stars), Worker Visualizer (nexu-io/open-design, 100k stars), Agent Worker Specialist (ruvnet/ruflo, 74k stars) and Loop Worker (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Opengantry?

iii-hq (a GitHub organization) maintains it in iii-hq/workers, which has 113 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 10, 2026.

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